Government and civil organizations around the world have long used fingerprints as the primary method of identifying people. In addition, fingerprints are the most accurate, user-friendly, and cost-effective biometric for use in a computerized identification system. In particular, this technology is used in the United States by the Department of Motor Vehicles of several state administrations, the FBI, MasterCard, the Secret Service, the Department of the Treasury, the National Security Agency, the Department of Defense, etc. By eliminating the need for passwords for end users, fingerprint recognition technology reduces the number of support calls and reduces network administration costs.

Typically, fingerprint recognition systems are divided into two types: for identification AFIS (Automatic Fingerprint Identification Systems) and for verification. In the first case, the prints of all ten fingers are used. Such systems are widely used in the judiciary. Verifiers typically operate on information about prints of one, less often several fingers. Scanning devices are generally of three types: optical, ultrasonic, and microchip-based.

One-time registration of a person's fingerprint on an optical scanner takes only a few minutes. A tiny CCD camera, available as a separate device or built into the keyboard, takes a snapshot of the fingerprint. Then, with the help of special algorithms, the resulting image is converted into a unique "template" - a map of microdots of this print, which are determined by the gaps and intersections of lines in it. This template (not the fingerprint itself) is then encrypted and written to a database to authenticate network users. Up to 40 - 50 microdots are stored in one template. At the same time, users do not have to worry about their privacy, since the fingerprint itself is not stored and cannot be recreated from microdots.

The advantage of ultrasonic scanning is the ability to determine the required characteristics on dirty fingers and even through thin rubber gloves. It is worth noting that modern recognition systems cannot be deceived, even by slipping them freshly severed fingers (a microchip measures the physical parameters of the skin), which, you see, is very important for Russia.

More than 50 different manufacturers are involved in the development of such systems. As for the cost of equipment, the construction of complexes for verification usually requires from several hundred to several thousand dollars. AFIS systems are much more expensive. For example, a software and hardware complex used by law enforcement agencies, designed to store information about 5 million people and perform about 5,000 searches per day, will cost several million dollars.

Retinal and iris identification

Quite reliable recognition is provided by systems that analyze the pattern of the iris of the human eye. The fact is that this characteristic is quite stable and does not change almost throughout life. Note also that the irises of the right and left eyes have a different pattern.

Iris scanners do not require the user to focus on a specific target, while the video image of the eye can be scanned from a distance of up to 1.5 m, which makes it possible to use such scanners, for example, in ATMs. Weakened vision does not prevent scanning and encoding of identifying parameters, as long as the iris is not damaged. Even a cataract - a clouding of the lens because it is behind the iris - does not interfere with the scan in any way.

A distinction is usually made between active and passive systems. In systems of the first type, the user must adjust the camera himself, moving it for more accurate aiming. Passive systems are easier to use because camera setup is automatic and very reliable.

Note that until now only two companies have produced equipment of this class: the most famous of them is IriScan ( http://www.iriscan.com/). The cost of biometric complexes of this company ranges from tens to several thousand dollars.

In biometric control systems that use the retinal pattern as an identification feature, the fundus is scanned by an optical system using infrared light. In this case, the pattern of the location of the blood vessels of the fundus is determined, or the reflective and absorbing characteristics of the retina are measured. It takes about 40 bytes to register the master image. The received information is stored in the system memory and used for comparison. Retinal scanners - denied access to registered users, and there are almost no cases of erroneous access. However, the image must be clear, and cataracts can adversely affect the quality of the picture. Typical authorization time is less than 60 s, analysis - 3 - 5 s. Despite the great advantages of this method (high reliability, impossibility of forgery), it has a number of disadvantages that limit its scope (relatively long analysis time, high cost, large dimensions of the scanning device, not very pleasant authorization procedure).

To ensure the confidentiality of information, various means of authorization and authentication of the user were proposed to provide him with the necessary physical access to data, financial resources, etc. Most modern authentication systems are based on the principle of obtaining, collecting and measuring biometric information, that is, information about certain physiological characteristics of a person.

The advantage of biometric identification systems over traditional ones (for example, PIN-code systems or password-based access systems) is that the person himself is identified. The characteristic used in these systems is an integral part of the personality, it cannot be lost, transferred, forgotten. Since the biometric characteristics of each individual are unique, they can be used to prevent theft or fraud. Today there are a large number of computerized rooms, vaults, research laboratories, blood banks, ATMs, military installations, etc., access to which is controlled by devices that scan the unique physiological characteristics of a person.

In recent years, the security of information networks, and in particular biometric security systems, has received the closest attention. Evidence of this is a huge number of articles devoted to a review of methods of human identification that have already become traditional and known to a wide range of readers: by fingerprints, by the retina and iris of the eye, by the features and structure of the face, by the geometry of the hand, by speech and handwriting.

The analysis of scientific, technical and periodical popular science literature makes it possible to systematize such systems in terms of the complexity of their development and the accuracy and reliability of the measurement results provided (Fig. 1). Some technologies are already widely adopted today, others are still being developed. In this article, we will give examples of systems of both the first and second groups.

Today's passwords

Fingerprint identification

To date, one of the most common biometric technologies is fingerprint identification technology. Systems using such technologies originate from forensic systems, when the criminal's fingerprint was entered into a file cabinet, and then compared with the presented fingerprint. Since then, a large number of advanced fingerprint scanning devices have appeared. Research in this area has shown that the human fingerprint does not change over time, and if the skin is damaged, the identical papillary pattern is completely restored. Obviously, due to these reasons, and also due to the fact that fingerprint scanning, unlike many other identification methods, does not cause discomfort to a person, this method has become the most common identification method. Another advantage of using this technique is a fairly high recognition accuracy. Companies that develop fingerprint scanning devices are constantly improving their algorithms and have succeeded significantly. For example, BioLink Technologies has released the BioLink U-Match Mouse (Fig. 2), a standard scroll wheel computer mouse with a built-in optical fingerprint scanner: interface - USB or COM+PS/2; protection against dummies and "lifeless" fingers; The use of advanced optical elements ensures high scan quality and recognition accuracy. The BioLink U-Match MatchBook biometric scanner is made as a separate device (Fig. 3), scanning time - 0.13 s, recognition time - 0.2 s, USB interface, protection against dummies is implemented. These devices demonstrate such recognition accuracy that the probability that an unauthorized user will gain access to protected information is equal to 1 in 1 billion fingerprint presentations.

In the domestic market, mice with a scanner from Siemens, keyboards with a built-in scanner from Cherry, as well as laptops with a fingerprint scanner are gaining popularity; devices from other manufacturers are also presented. Therefore, if the head of the enterprise decides to replace the outdated security system with more advanced information protection tools, he will have plenty to choose from.

An analysis of the global biometric market shows that fingerprint recognition technologies represent 50% of the biometric market, and together with forensic systems, all 80%. According to the results of 2001, the International Biometric Group stated that fingerprint identification technologies still occupy a leading position among all biometric technologies on the market.

To use the standard biometric fingerprint recognition system, the user must first register with the system. At the same time, there is no reason to fear that your fingerprint will be stored in the device’s memory - most systems do not store in memory the real image of the fingerprint, but only a digital template, according to which it is impossible to restore the real image, so user rights are not violated in any way. So, when using BioLink Technologies devices, the fingerprint image is instantly converted into a small digital code (only 512 bytes in size).

The introduction of biometric protection does not always require the replacement of the existing security system. It is often possible to replace passwords with a user's biometric passport at minimal cost. For example, solutions from BioLink Technologies allow you to install a biometric security system on top of a standard password security system. In this case, there is a completely painless replacement of passwords for fingerprints. Thus, you can securely protect the login to the operating system (Windows NT/2000, Windows 95/98, Novell NetWare) and the forced lock, screen saver, and sleep modes, as well as replace the standard application program protection with fingerprint protection. All these basic functions, as well as many other features, are implemented by the BioLink Authentication Center version 4.2 software - the only fully Russified system of this class to date. At the same time, fingerprint models are stored centrally - on the Authenteon authentication hardware and software system (Fig. 4). The server provides secure storage of up to 5,000 fingerprint models, which cannot be used to reproduce a real fingerprint image, and other secret information. In addition, the Authenteon server is a centralized user administration, as well as the ability for an administrator to easily give registered users different access privileges to different resources without re-registration. Server fault tolerance is implemented as follows: the server is a case in which two independent physical servers are placed, which makes it possible to hot-swap and replicate the database to a running server.

Since Internet applications (Internet banking, e-commerce, corporate portals) are becoming increasingly popular, BioLink developers have taken care of the possibility of introducing fingerprint biometric identification into Internet applications. Thus, any company, enterprise or institution can securely protect sensitive information.

BioLink Technologies solutions are primarily designed for medium and large enterprises. At the same time, a comprehensive Russified solution (software + input devices + hardware server) can be best integrated with information and ERP systems used in the enterprise, which allows, on the one hand, to significantly reduce the cost of administering password systems, and on the other hand, to reliably secure confidential information from unauthorized access both from outside and inside the enterprise.

In addition, there is an opportunity to solve another urgent problem - to significantly reduce the risks when transferring data to financial, banking and other systems that carry out important transactions using the Internet.

Iris identification systems

As follows from Fig. 1, the greatest accuracy and reliability at the present stage is provided by biometric identification systems based on the analysis and comparison of the iris. After all, eyes with the same iris, even in completely identical twins, do not exist. Formed in the first year of life, this parameter remains unique for a person throughout the entire time of his existence. This identification method differs from the first one in that it is more difficult to use, the equipment is more expensive, and the registration conditions are stricter.

As an example of a modern identification system based on the analysis of the iris, it is appropriate to cite a solution from LG.

The IrisAccess system allows you to scan the iris pattern in less than a second, process and compare it with 4,000 other records that it stores in its memory, and then send the appropriate signal to the security system. The technology is completely non-contact (Fig. 5). Based on the image of the iris, a compact digital code of 512 bytes is built. The device has high reliability compared to most known biometric control systems (Fig. 6), maintains a large database, issues sound instructions in Russian, and allows integrating access cards and PIN keyboards into the system. One controller supports four readers. The system can be integrated into the LAN.

The IrisAccess 3000 consists of an EOU3000 optical enroller, a ROU3000 remote optical enroller, an ICU3000 authentication control unit, an image capture board, a door interface board, and a PC server.

If multiple inputs need to be controlled, a number of remote devices, including the ICU3000 and ROU3000, can be connected to the PC server via a local area network (LAN). Descriptions of the main components of the system are provided in the sidebar.

The organization of access control and a schematic diagram of the deployment of a security system based on IrisAccess from LG are shown in fig. 7, .

Speech recognition systems

The lowest position in Fig. 1 - both in terms of labor intensity and in terms of accuracy - are occupied by identification systems based on speech recognition. The reasons for the introduction of these systems are the ubiquity of telephone networks and the practice of embedding microphones in computers and peripherals such as cameras. The disadvantages of such systems include factors affecting the recognition results: interference in microphones, the influence of the environment on the recognition results (noise), pronunciation errors, different emotional state of the standard being checked at the time of registration and during each identification, the use of different recording devices during records of standards and identification, interference in low-quality data channels, etc.

Passwords of the future

We have given examples of biometric devices that are already widely used for access control, but scientific and technological progress does not stand still, and therefore the range of technologies that can be used in security systems is constantly expanding. A number of biometric technologies are currently under development, some of which are considered very promising. Therefore, let's talk about technologies that have not yet found mass adoption, but after a while they may well stand on a par with the most reliable technologies used today. We included the following technologies in this list:

1. building a face thermogram based on information from an infrared radiation sensor;
2. analysis of DNA characteristics;
3. analysis of the dynamics of strokes on the computer keyboard when typing text;
4. analysis of the structure of the skin and epithelium on the fingers based on digital ultrasound information;
5. handprint analysis;
6. analysis of the shape of the auricle;
7. analysis of human gait characteristics;
8. analysis of individual human odors.

Let's consider the essence of these methods in more detail. The technology for constructing and analyzing a thermogram (Fig. 9) is one of the latest achievements in the field of biometrics. As scientists have found, the use of infrared cameras gives a unique picture of objects under the skin of the face. Different densities of bone, fat and blood vessels are strictly individual and determine the thermographic picture of the user's face. According to scientific conclusions, the thermogram of the face is unique, as a result of which even absolutely similar twins can be confidently distinguished. Additional properties of this approach include its invariance with respect to any cosmetic or cosmetological changes, including plastic surgery, make-up changes, etc., as well as the secrecy of the registration procedure.

The technology based on the analysis of DNA characteristics, or, as scientists call it, the method of genomic identification (Fig. 10), is, apparently, although the longest-term, but also the most promising of the identification systems. Currently, this control method is too slow and difficult to automate. The method is based on the fact that there are polymorphic loci in human DNA (locus is the position of the chromosome (in a gene or allele), often having 8-10 alleles. Determining the set of these alleles for several polymorphic loci in a particular individual allows you to get a kind of genomic map that is characteristic only for that person.The accuracy of this method is determined by the nature and number of analyzed polymorphic loci and today allows to reach an error level of 1 per 1 million people.

The dynamics of strokes on the computer keyboard when typing text, or keyboard handwriting, analyzes the way (rhythm) of the user typing a particular phrase. There are two types of keyboard handwriting recognition systems. The first are designed to authenticate the user when trying to gain access to computing resources. The latter carry out monitoring control after granting access and block the system if a different person to whom access was initially granted started working on the computer. The rhythm of the keyboard, as studies by a number of firms and organizations have shown, is a rather individual characteristic of the user and is quite suitable for his identification and authentication. To measure it, the time intervals are estimated either between strokes when typing characters located in a certain sequence, or between the moment the key is hit and the moment it is released when typing each character in this sequence. Although the second method is considered more effective, the best result is achieved by using both methods together. A distinctive feature of this method is its low cost, since no equipment other than a keyboard is required to analyze information. It should be noted that at the moment this technology is under development, and therefore it is difficult to assess the degree of its reliability, especially given the high requirements for security systems.

To identify a person by hand, several biometric parameters are used - this is the geometric shape of the hand or fingers, the location of the subcutaneous blood vessels of the palm, the pattern of lines on the palm.

Handprint analysis technology began to develop relatively recently, but already has certain achievements. The reason for the development of this technology was the fact that fingerprint recognition devices have a drawback - they only need clean hands, and the system may not recognize a dirty fingerprint. Therefore, a number of development companies have focused on technology that analyzes not the pattern of lines on the skin, but the outline of the palm, which also has an individual character. So, in the middle of last year in the UK, the development of a new computer system began, which will allow identifying suspects by fingerprints. A similar fingerprint system has been successfully used by British police for three years now. But fingerprints alone, according to criminologists, are often not enough. Up to 20% of the footprints left at a crime scene are handprints. However, their analysis by traditional means is rather laborious. Computerization of this process will allow the use of palm prints more widely and will lead to a significant increase in crime detection. The system is expected to be in place by early 2004 and will cost the Home Office £17 million to set up. It should be noted that palm scanning devices are usually expensive, and therefore it is not so easy to equip a large number of workplaces with them.

The auricle shape analysis technology is one of the latest approaches in human biometric identification. Even an inexpensive webcam can produce fairly reliable samples for comparison and identification. It should be noted that, since this method has not been sufficiently studied, we could not find reliable information about the current state of affairs in the scientific and technical literature.

The ability of dogs to distinguish people by smell and the presence of a genetic influence on body odor make it possible to consider this characteristic, despite its dependence on customs and individual habits (use of perfumery, diet, use of drugs, etc.), as promising in terms of use for biometric personality authentication. Currently, the development of "electronic nose" systems is already underway (Fig. 11). As a rule, an “electronic nose” is a complex system consisting of three functional units operating in the mode of periodic perception of odorous substances: a sampling and sample preparation system, a line or matrix of sensors with specified properties, and a signal processing unit of the sensor matrix. This technology, like ear shape analysis, still has a long way to go before it can meet biometric requirements.

In conclusion, it is still too early to predict where, how and in what form reliable biometric services will eventually be provided. But it is absolutely clear that it is impossible to do without biometric identification if positive, reliable and irrefutable verification results are to be obtained. Therefore, it is possible that in the very near future passwords and PIN codes will give way to new, more reliable means of authorization and authentication.

ComputerPress 3 "2002

In the second part of the article (the first one was published in RS Magazin/RE, 1/2004), the main methods of fingerprint recognition, algorithms for building recognition systems and some methods of protection against dummies are disclosed. But before moving on to these questions, let's consider what it is and how a papillary pattern appears on the surface of the fingers.

Human skin consists of two layers: the epidermis (epidermis), the outer layer, and the dermis (derma), the deeper layer.

At the fifth month of human intrauterine development, the dermis, previously even, becomes uneven and begins to take on the appearance of many dermal tubercles alternating with each other (sometimes they are called papillae). On the surface of the fingers, these tubercles fold into rows. The epidermis repeats the structure of the outer layer of the dermis and forms small folds that reflect and repeat the course of rows of dermal tubercles.

The folds that we see on the surface of the skin with the naked eye are called papillary lines (from the Latin parillae - papillae) and are separated from each other by shallow grooves. At the tops of the folds, the ridges of the papillary lines, there are numerous tiny pores - the external openings of the excretory ducts of the sweat glands of the skin. Papillary lines on the surface of the fingers form various patterns called papillary patterns.

Finally, the papillary pattern on the surface of the fingers is formed by the seventh month of intrauterine development. Since that time, the grooves formed on the surface of the fingers remain unchanged throughout a person's life.

The structure of the upper layer of the skin of human fingers, the epidermis, is such that it protects the dermis, i.e., the skin itself, from mechanical damage. After any damage to the epidermis that does not affect the dermal tubercles, the papillary pattern is restored in its original form during the healing process, which has been confirmed by numerous experiments. If the dermal tubercles are damaged, then a scar is formed, which deforms the papillary pattern to a certain extent, but does not fundamentally change the original general pattern, and the scar itself can be used as a secondary sign in identification.

In Russian traditional fingerprinting, papillary patterns of the fingers are divided into three main types: arc (about 5% of all prints), loop (65%) and curl (30%); for each type, a more detailed classification into subtypes is carried out. However, within the framework of this article, methods of automated identification of a person, and not fingerprinting, will be considered first of all.

Recognition methods

Depending on the quality of the fingerprint image received from the scanner, some characteristic features of the surface of the fingers can be distinguished on it, which can later be used for identification.

At the simplest technical level, for example, with a resolution of 300-500 dpi obtained from a finger surface image, it shows a fairly large number of small details (minutiae) by which they can be classified, but, as a rule, only two types of pattern details (special points): endpoints, where the papillary lines clearly end, and branching points, where the papillary lines bifurcate.

If it is possible to obtain an image of the surface of the finger with a resolution of about 1000 dpi, then it is possible to detect details of the internal structure of the papillary lines themselves, in particular the pores of the sweat glands, and, accordingly, use their location for identification. However, due to the difficulty of obtaining images of this quality in non-laboratory conditions, this method is not widely used.

With automated fingerprint recognition (unlike traditional fingerprinting), there are much fewer problems associated with various external factors that affect the recognition process itself. When obtaining fingerprints using the ink method (using rollback), it is important to exclude or at least minimize the displacement or rotation of the finger, pressure changes, changes in the quality of the skin surface, etc. From electronic inkless scanners, obtain a fingerprint image with sufficient processing quality is much easier. The quality of the image of the papillary pattern of the finger obtained from the scanner is one of the main criteria on which the chosen algorithm for the formation of a fingerprint convolution and, consequently, the identification of a person depends.

Currently, there are three classes of fingerprint comparison algorithms.

1. Correlation comparison- two fingerprint images are superimposed on each other, and the correlation (in intensity level) between the corresponding pixels calculated for different alignments of the images relative to each other (for example, by different displacements and rotations) is calculated; according to the corresponding coefficient, a decision is made about the identity of the prints. Due to the complexity and duration of this algorithm, especially when solving identification problems (one-to-many comparison), systems based on it are practically not used now.

2. Comparison by singular points- based on one or more fingerprint images from the scanner, a template is formed, which is a two-dimensional surface on which end points and branching points are highlighted. These points are also selected on the scanned image of the print, their map is compared with the template, and a decision is made on the identity of the prints based on the number of matched points. In the work of algorithms of this class, the mechanisms of correlation comparison are implemented, but when comparing the position of each of the points that supposedly correspond to each other. Due to the simplicity of implementation and speed of operation, algorithms of this class are the most widely used. The only significant drawback of this comparison method is the rather high requirements for the quality of the resulting image (about 500 dpi).

3. Comparison by pattern- in this comparison algorithm, the structural features of the papillary pattern on the surface of the fingers are directly used. The fingerprint image received from the scanner is divided into many small cells (the size of the cells depends on the required accuracy). The location of the lines in each cell is described by the parameters of a certain sinusoidal wave, i.e., the initial phase shift, the wavelength, and the direction of its propagation are specified. The print received for comparison is aligned and brought to the same form as the template. Then the parameters of the wave representations of the corresponding cells are compared. The advantage of comparison algorithms of this class is that they do not require a high quality image.

Within the framework of the article, we will restrict ourselves to a generalized description of the operation of each of the classes of algorithms; in practice, this all looks much more complicated in terms of both the mathematical apparatus and image processing. Note that in automated identification there are several problems associated with the difficulty of scanning and recognizing certain types of fingerprints, especially for young children, since their fingers are very small in order to obtain their prints with acceptable detail even with good equipment. for recognition. In addition, about 1% of adults have such unique fingerprints that to work with them, it is necessary to develop specialized processing algorithms or make an exception in the form of a personal rejection of biometrics for them.

Approaches to protection against dummies

The problem of protecting a wide variety of biometric systems from dummies of biometric identifiers is one of the most difficult both for the entire region and, first of all, for fingerprint recognition technology. This is due to the fact that fingerprints are relatively easy to obtain compared to, for example, an iris or a 3D hand shape, and making a fake fingerprint looks like an easier task as well. We will not touch on the technologies for making dummies of fingerprints; enough information has recently appeared about this in many sources. Let us dwell on the main methods and approaches to protection against them.

In general, all methods can be divided into two groups.

1. Technical- protection methods implemented either at the level of the software that works with the image, or at the level of the reader. Let's consider them in more detail.

Protection at the level of the reader lies in the fact that the scanner itself implements an image acquisition algorithm that allows you to get a fingerprint only from a “live” finger, and not from a dummy - for example, this is how the fiber optic scanners described in the first part of the article work;

Additional characteristic protection consists in obtaining some additional characteristic using the scanning device, according to which it is possible to decide whether the provided identifier is a dummy. For example, with the help of ultrasonic scanners it is possible to obtain information about the presence of a pulse in the finger, in some high-resolution optical scanners it is possible to determine the presence of sweat particles in the image, etc. Almost every manufacturer has such a “proprietary” characteristic, which, as a rule, , is not said, because, knowing it, it is much easier to find a way to bypass this protection;

Protection according to previous data, when the fingerprint of the last finger that touched the scanner remains on its surface, which can be used in the manufacture of a dummy. In this case, they are protected by storing the last few images from the scanner (their number is different for each manufacturer), with which any new image is first compared. And since it is impossible to apply a finger to the scanner in exactly the same way twice, in case of any coincidence, a decision is made to use a dummy.

2. Organizational- the essence of these methods is to organize authentication processes in such a way as to make it difficult or impossible to use a dummy. Let's consider these methods.

The complexity of the identification process. The fingerprint enrollment process enrolls multiple fingers per user (ideally all 10). Then, directly during the authentication process, the user is asked to check several fingers in an arbitrary sequence, which makes it much more difficult to enter the system using a dummy;

Multibiometry or multifactorial biometrics. Here, several biometric technologies are implemented for authentication, such as fingerprint and face shape or retina, etc.;

Multi-factor authentication. To enhance security, a combination of authentication methods is used, such as biometrics and smart cards or e-token.

Conclusion

This article provided a general description of the internal features of the most widely used biometric technology. Many aspects of building systems based on automated human fingerprint recognition have not yet been considered, such as image processing and normalization, features of building corporate network systems, biometric authentication servers, types of attacks on biometric systems and methods of protection against them, etc. ., each of which is a separate topic for a large material. Fingerprint recognition is becoming more and more interesting in the light of the reforms of Russian foreign and domestic passports planned in the next few years and the entry rules already being implemented in some countries on visas containing biometric data, and primarily fingerprints.

PC Magazine/Russian Edition

ZlodeiBaal August 11, 2011 at 09:54 pm

Modern biometric identification methods

• Information Security

Recently, many articles have appeared on Habré devoted to Google's face identification systems. To be honest, many of them smell like journalism and, to put it mildly, incompetence. And I wanted to write a good article on biometrics, it's not my first! There are a couple of good articles on biometrics on Habré - but they are quite short and incomplete. Here I will try to briefly outline the general principles of biometric identification and the modern achievements of mankind in this matter. Including in identification by persons.

The article has a , which, in fact, is its prequel.

As a basis for the article, a joint publication with a colleague in a journal (BDI, 2009), revised for modern realities, will be used. Habré does not have a colleague yet, but he supported the publication of the revised article here. At the time of publication, the article was a brief overview of the modern market for biometric technologies, which we conducted for ourselves before launching our product. The value judgments about applicability put forward in the second part of the article are based on the opinions of people who used and implemented the products, as well as on the opinions of people involved in the production of biometric systems in Russia and Europe.

general information

Let's start with the basics. In 95% of cases, biometrics is inherently mathematical statistics. And matstat is an exact science, algorithms from which are used everywhere: in radars and in Bayesian systems. Errors of the first and second kind can be taken as the two main characteristics of any biometric system). In radar theory, they are usually called “false alarms” or “target misses”, and in biometrics, the most established concepts are FAR (False Acceptance Rate) and FRR (False Rejection Rate). The first number characterizes the probability of a false match of the biometric characteristics of two people. The second is the probability of denying access to a person with a permit. The system is better, the smaller the FRR value at the same FAR values. Sometimes a comparative characteristic of EER is also used, which determines the point at which the FRR and FAR graphs intersect. But it is not always representative. More details can be seen, for example,.
The following may be noted: if FAR and FRR for open biometric databases are not given in the characteristics of the system, then no matter what the manufacturers declare about its characteristics, this system is most likely incapacitated or much weaker than its competitors.
But not only FAR and FRR determine the quality of a biometric system. If this were the only way, then the leading technology would be DNA recognition of people, for which FAR and FRR tend to zero. But it is obvious that this technology is not applicable at the current stage of human development! We have developed several empirical characteristics to assess the quality of the system. "Forgery resistance" is an empirical measure that summarizes how easy it is to spoof a biometric identifier. "Environmental stability" is a characteristic that empirically evaluates the stability of the system under various external conditions, such as changes in lighting or room temperature. "Ease of use" shows how difficult it is to use a biometric scanner, whether identification is possible "on the go". An important characteristic is the "Speed ​​of work", and "The cost of the system". Do not forget that the biometric characteristic of a person can change over time, so if it is unstable, this is a significant minus.
The abundance of biometric methods is amazing. The main methods using static biometric characteristics of a person are identification by papillary pattern on the fingers, iris, facial geometry, retina, hand vein pattern, hand geometry. There is also a family of methods that use dynamic characteristics: identification by voice, handwriting dynamics, heart rate, gait. Below is the distribution of the biometric market a couple of years ago. In every second source, these data fluctuate by 15-20 percent, so this is just an estimate. Also here, under the concept of “hand geometry”, two different methods are hidden, which will be discussed below.


In the article, we will consider only those characteristics that are applicable in access control and management systems (ACS) or in tasks close to them. By virtue of their superiority, these are primarily static characteristics. Of the dynamic characteristics at the moment, only voice recognition has at least some statistical significance (comparable to the worst static algorithms FAR ~ 0.1%, FRR ~ 6%), but only in ideal conditions.
To get a feel for the likelihood of FAR and FRR, one can estimate how often false matches will occur if an identification system is installed at a gated organization with N staff. The false match probability of a fingerprint received by the scanner for a database of N fingerprints is FAR∙N. And every day, about N people also pass through the access control point. Then the error probability per working day is FAR∙(N∙N). Of course, depending on the goals of the identification system, the probability of an error per unit of time can vary greatly, but if one error per working day is accepted, then:
(1)
Then we get that the stable operation of the identification system at FAR=0.1% =0.001 is possible with the number of personnel N≈30.

Biometric scanners

Today, the concepts of "biometric algorithm" and "biometric scanner" are not necessarily interconnected. The company can produce these elements individually, or together. The greatest differentiation of scanner manufacturers and software manufacturers has been achieved in the papillary finger pattern biometrics market. The smallest 3D face scanner on the market. In fact, the level of differentiation largely reflects the development and saturation of the market. The more choice - the more the theme is worked out and brought to perfection. Different scanners have a different set of abilities. Basically, this is a set of tests to check whether a biometric object has been tampered with or not. For finger scanners, this can be a relief check or a temperature check, for eye scanners, this can be a pupil accommodation check, for face scanners, face movement.
Scanners have a very strong influence on the received FAR and FRR statistics. In some cases, these figures can change dozens of times, especially in real conditions. Usually the characteristics of the algorithm are given for some “ideal” base, or just for a well-suited one, where blurry and blurry frames are thrown out. Only a few algorithms honestly indicate both the base and the full FAR / FRR output for it.

And now in more detail about each of the technologies.

Fingerprints

Dactyloscopy (fingerprint recognition) is the most developed biometric method of personal identification to date. The catalyst for the development of the method was its widespread use in forensic science in the 20th century.
Each person has a unique papillary fingerprint pattern, which makes identification possible. Typically, algorithms use characteristic points on fingerprints: the end of the line of the pattern, the branching of the line, single points. Additionally, information about the morphological structure of the fingerprint is involved: the relative position of closed lines of the papillary pattern, "arched" and spiral lines. The features of the papillary pattern are converted into a unique code that preserves the information content of the print image. And it is the "fingerprint codes" that are stored in the database used for searching and comparing. The time for translating a fingerprint image into a code and its identification usually does not exceed 1 s, depending on the size of the base. The time spent on raising a hand is not taken into account.

As a source of data for FAR and FRR, VeriFinger SDK statistics obtained using the U.are.U DP fingerprint scanner were used. Over the past 5-10 years, the characteristics of recognition by the finger have not stepped forward much, so the figures given show a good average of modern algorithms. The VeriFinger algorithm itself has won the International Fingerprint Verification Competition for several years, where fingerprint recognition algorithms competed.

The typical FAR value for the fingerprint recognition method is 0.001%.
From formula (1) we obtain that the stable operation of the identification system at FAR=0.001% is possible with the number of personnel N≈300.

Advantages of the method. High reliability - the statistical indicators of the method are better than those of the methods of identification by face, voice, painting. Low cost devices that scan the fingerprint image. A fairly simple procedure for scanning a fingerprint.
Disadvantages: the papillary fingerprint pattern is very easily damaged by small scratches, cuts. People who have used scanners in businesses with several hundred employees report a high rate of scan failure. Many of the scanners do not adequately treat dry skin and do not let old people through. When communicating at the last MIPS exhibition, the head of the security service of a large chemical enterprise said that their attempt to introduce finger scanners at the enterprise (scanners of various systems were tried) failed - the minimal exposure of employees' fingers to chemicals caused a failure in the security systems of the scanners - the scanners declared the fingers fake. There is also a lack of security against fingerprint forgery, partly due to the widespread use of the method. Of course, not all scanners can be fooled by methods from MythBusters, but still. For some people with “inappropriate” fingers (body temperature, humidity), the probability of access being denied can reach 100%. The number of such people varies from fractions of a percent for expensive scanners to ten percent for inexpensive ones.
Of course, it is worth noting that a large number of shortcomings are caused by the widespread use of the system, but these shortcomings do exist and they appear very often.

Market situation

Currently, fingerprint recognition systems occupy more than half of the biometric market. Many Russian and foreign companies are engaged in the production of access control systems based on the fingerprint identification method. Due to the fact that this direction is one of the oldest, it has received the greatest distribution and is by far the most developed. Fingerprint scanners have come a long way indeed. Modern systems are equipped with various sensors (temperature, pressing force, etc.), which increase the degree of protection against counterfeiting. Every day systems become more and more convenient and compact. In fact, the developers have already reached a certain limit in this area, and there is nowhere to develop the method further. In addition, most companies produce ready-made systems that are equipped with everything you need, including software. There is simply no need for integrators in this area to assemble the system on their own, since it is unprofitable and will take more time and effort than buying a ready-made and already inexpensive system, the more choice will be really wide.
Among foreign companies involved in fingerprint recognition systems, one can note SecuGen (USB scanners for PCs, scanners that can be installed in enterprises or built into locks, SDK and software for connecting the system to a computer); Bayometric Inc. (fingerprint scanners, TAA/Access control systems, fingerprint SDKs, embedded fingerprint modules); DigitalPersona Inc. (USB-scanners, SDK). The following companies operate in Russia in this area: BioLink (fingerprint scanners, biometric access control devices, software); Sonda (fingerprint scanners, biometric access control devices, SDK); SmartLock (fingerprint scanners and modules), etc.

Iris

The iris of the eye is a unique human characteristic. The iris pattern is formed in the eighth month of fetal development, finally stabilizes at the age of about two years and practically does not change throughout life, except as a result of severe injuries or severe pathologies. The method is one of the most accurate among biometric methods.
The iris identification system is logically divided into two parts: an image capture device, its primary processing and transmission to a computer, and a computer that compares the image with images in the database and transmits a command on admission to the actuator.
The time of primary image processing in modern systems is approximately 300-500ms, the speed of comparing the resulting image with the base has a level of 50000-150000 comparisons per second on a conventional PC. This speed of comparison does not impose restrictions on the application of the method in large organizations when used in access systems. When using specialized calculators and search optimization algorithms, it becomes even possible to identify a person among the inhabitants of an entire country.
I can immediately answer that I am somewhat biased and have a positive attitude towards this method, since it was in this field that we launched our startup. A paragraph at the end will be devoted to a small self-promotion.

Statistical characteristics of the method

The characteristics of FAR and FRR for the iris are the best in the class of modern biometric systems (with the possible exception of the retinal recognition method). The article presents the characteristics of the iris recognition library of our algorithm - EyeR SDK, which correspond to the VeriEye algorithm tested on the same databases. CASIA databases obtained by their scanner were used.

The characteristic value of FAR is 0.00001%.
According to formula (1), N≈3000 is the number of personnel of the organization, at which the identification of an employee occurs quite stably.
Here it is worth noting an important feature that distinguishes the iris recognition system from other systems. In the case of using a camera with a resolution of 1.3 MP, you can capture two eyes in one frame. Since the FAR and FRR probabilities are statistically independent probabilities, when recognizing in two eyes, the FAR value will approximately equal the square of the FAR value for one eye. For example, for a FAR of 0.001% using two eyes, the probability of a false tolerance would be 10-8%, with FRR only twice as high as the corresponding FRR value for one eye with FAR=0.001%.

Advantages and disadvantages of the method

Advantages of the method. Statistical reliability of the algorithm. Capturing an image of the iris can be performed at a distance of several centimeters to several meters, while the physical contact of a person with the device does not occur. The iris is protected from damage - which means it will not change over time. It is also possible to use a high number of methods that protect against forgery.
Disadvantages of the method. The price of a system based on the iris is higher than the price of a system based on finger recognition or face recognition. Low availability of ready-made solutions. Any integrator who comes to the Russian market today and says “give me a ready-made system” will most likely break off. For the most part, expensive turnkey systems are sold, installed by large companies such as Iridian or LG.

Market situation

At the moment, the share of iris identification technologies in the global biometric market is, according to various estimates, from 6 to 9 percent (while fingerprint recognition technologies occupy more than half of the market). It should be noted that from the very beginning of the development of this method, its strengthening in the market was slowed down by the high cost of equipment and components necessary to assemble an identification system. However, with the development of digital technologies, the cost of a single system began to decline.
The leader in software development in this area is Iridian Technologies.
Entry to the market for a large number of manufacturers was limited by the technical complexity of scanners and, as a result, their high cost, as well as the high price of software due to the monopoly position of Iridian in the market. These factors allowed only large companies to develop in the field of iris recognition, most likely already engaged in the production of some components suitable for the identification system (high-resolution optics, miniature cameras with infrared illumination, etc.). Examples of such companies are LG Electronics, Panasonic, OKI. They entered into an agreement with Iridian Technologies, and as a result of joint work, the following identification systems appeared: Iris Access 2200, BM-ET500, OKI IrisPass. In the future, improved system models arose, thanks to the technical capabilities of these companies to independently develop in this area. It should be said that the above companies also developed their own software, but in the end, in the finished system, they prefer the software of Iridian Technologies.
The Russian market is dominated by the products of foreign companies. Even though it's hard to buy. For a long time, Papillon assured everyone that they had iris recognition. But even representatives of RosAtom, their direct purchaser, for whom they made the system, say that this is not true. At some point, some other Russian company appeared, which made iris scanners. I don't remember the name now. They bought the algorithm from someone, perhaps from the same VeriEye. The scanner itself was a system 10-15 years old, by no means non-contact.
In the last year, a couple of new manufacturers entered the world market due to the expiration of the primary patent for recognizing a person by eyes. The most trusted of them, in my opinion, deserves AOptix. At least their preview and documentation does not arouse suspicion. The second company is SRI International. Even at first glance, to a person involved in iris recognition systems, their videos seem very false. Although I would not be surprised if in reality they can do something. Both systems do not show data on FAR and FRR, and also, apparently, are not protected from fakes.

face recognition

There are many face geometry recognition methods. All of them are based on the fact that the facial features and the shape of the skull of each person are individual. This area of ​​​​biometrics seems attractive to many, because we recognize each other primarily by the face. This area is divided into two areas: 2-D recognition and 3-D recognition. Each of them has advantages and disadvantages, but much also depends on the scope and requirements for a particular algorithm.
I will briefly talk about 2-d and move on to one of the most interesting methods today - 3-d.

2D face recognition

2-D face recognition is one of the most statistically inefficient biometric methods. It appeared quite a long time ago and was used mainly in forensic science, which contributed to its development. Subsequently, computer interpretations of the method appeared, as a result of which it became more reliable, but, of course, it was inferior and every year it is more and more inferior to other biometric methods of personal identification. Currently, due to poor statistical performance, it is used in multimodal or, as it is also called, cross-biometrics, or in social networks.

Statistical characteristics of the method

For FAR and FRR, data for the VeriLook algorithms were used. Again, for modern algorithms, it has very ordinary characteristics. Sometimes algorithms with an FRR of 0.1% with a similar FAR flash by, but the bases on which they were obtained are very doubtful (cut out background, the same facial expression, the same hairstyle, lighting).

The characteristic value of FAR is 0.1%.
From formula (1) we obtain N≈30 - the number of personnel of the organization, at which the identification of an employee occurs quite stably.
As can be seen, the statistical indicators of the method are quite modest: this eliminates the advantage of the method that it is possible to conduct covert shooting of faces in crowded places. It's funny to see how a couple of times a year another project is funded to detect criminals through video cameras installed in crowded places. Over the past ten years, the statistical characteristics of the algorithm have not improved, and the number of such projects has increased. Although, it is worth noting that the algorithm is quite suitable for leading a person in a crowd through many cameras.

Advantages and disadvantages of the method

Advantages of the method. With 2-D recognition, unlike most biometric methods, expensive equipment is not required. With the appropriate equipment, the possibility of recognition at considerable distances from the camera.
Flaws. Low statistical significance. There are requirements for lighting (for example, the faces of people entering from the street on a sunny day cannot be registered). For many algorithms, the unacceptability of any external interference, such as glasses, a beard, some elements of a hairstyle. Mandatory frontal image of the face, with very small deviations. Many algorithms do not take into account possible changes in facial expressions, that is, the expression must be neutral.

3-D face recognition

The implementation of this method is a rather difficult task. Despite this, there are currently many methods for 3-D face recognition. The methods cannot be compared with each other as they use different scanners and bases. far from all of them issue FAR and FRR, completely different approaches are used.
The transitional method from 2-d to 3-d is a method that implements the accumulation of information about a person. This method has better characteristics than the 2d method, but just like it uses only one camera. When entering the subject into the database, the subject turns his head and the algorithm connects the image together, creating a 3d template. And when recognizing, several frames of the video stream are used. This method is rather experimental and I have never seen implementations for ACS systems.
The most classic method is the template projection method. It consists in the fact that a grid is projected onto the object (face). Next, the camera takes pictures at a speed of tens of frames per second, and the resulting images are processed by a special program. A beam falling on a curved surface bends - the greater the curvature of the surface, the stronger the bending of the beam. Initially, this used a source of visible light supplied through the "blinds". Then visible light was replaced by infrared, which has a number of advantages. Usually, at the first stage of processing, images are discarded in which the face is not visible at all or there are foreign objects that interfere with identification. Based on the obtained images, a 3-D model of the face is restored, on which unnecessary interference (hairstyle, beard, mustache and glasses) is highlighted and removed. Then the model is analyzed - anthropometric features are highlighted, which are eventually recorded in a unique code entered into the database. Image capture and processing time is 1-2 seconds for the best models.
Also, the method of 3-d recognition based on an image obtained from several cameras is gaining popularity. An example of this is Vocord with its 3d scanner. This method gives positioning accuracy, according to the assurances of the developers, higher than the template projection method. But, until I see FAR and FRR at least in their own database, I won’t believe it !!! But it has been developed for 3 years already, and progress at exhibitions is not yet visible.

Statistical indicators of the method

Full data on FRR and FAR for algorithms of this class are not openly provided on the websites of manufacturers. But for the best Bioscript models (3D EnrolCam, 3D FastPass) working by the template projection method with FAR = 0.0047% FRR is 0.103%.
It is believed that the statistical reliability of the method is comparable to the reliability of the fingerprint identification method.

Advantages and disadvantages of the method

Advantages of the method. No need to contact the scanning device. Low sensitivity to external factors, both on the person himself (the appearance of glasses, a beard, a change in hairstyle), and in his environment (illumination, turning of the head). High level of security, comparable to fingerprint identification.
Disadvantages of the method. Expensive equipment. The complexes available for sale were even more expensive than iris scanners. Changes in facial expressions and noise on the face degrade the statistical reliability of the method. The method is not yet well developed, especially in comparison with fingerprinting, which has been used for a long time, which makes it difficult to widely use it.

Market situation

Facial geometry recognition is one of the "three big biometrics" along with fingerprint and iris recognition. I must say that this method is quite common, and so far it is given preference over recognition by the iris of the eye. The share of face geometry recognition technologies in the total volume of the global biometric market can be estimated at 13-18 percent. In Russia, this technology is also showing more interest than, for example, identification by the iris. As mentioned earlier, there are many 3-D recognition algorithms. For the most part, companies prefer to develop turnkey systems that include scanners, servers, and software. However, there are those who offer the consumer only the SDK. To date, we can note the following companies involved in the development of this technology: Geometrix, Inc. (3D face scanners, software), Genex Technologies (3D face scanners, software) in the USA, Cognitec Systems GmbH (SDK, special computers, 2D cameras) in Germany, Bioscrypt (3D face scanners, software) is a subsidiary of the American company L- 1 Identity Solutions.
In Russia, Artec Group companies (3D face scanners and software) are working in this direction - a company headquartered in California, and development and production are carried out in Moscow. Also, several Russian companies own 2D face recognition technology - Vocord, ITV, etc.
In the field of 2D face recognition, the main subject of development is software, because Conventional cameras are great at capturing images of faces. The solution to the problem of face recognition has reached a dead end to some extent - for several years now, there has been practically no improvement in the statistical indicators of algorithms. In this area, there is a systematic "work on the bugs".
3D face recognition is now a much more attractive area for developers. It employs many teams and regularly hears about new discoveries. Many of the works are in a "just about to be released" state. But so far, only old offers are on the market; in recent years, the choice has not changed.
One of the interesting points that I sometimes think about and which, perhaps, Habr will answer: is the accuracy of kinect enough to create such a system? There are quite a few projects for pulling out a 3d model of a person through it.

Recognition by the veins of the hand

This is a new technology in the field of biometrics, its widespread use began only 5-10 years ago. The infrared camera takes pictures of the outside or inside of the hand. The pattern of veins is formed due to the fact that blood hemoglobin absorbs infrared radiation. As a result, the degree of reflection is reduced and the veins are visible on the camera as black lines. A special program based on the received data creates a digital convolution. No human contact with the scanning device is required.
The technology is comparable in reliability to recognition by the iris of the eye, surpassing it in some ways, and inferior in some ways.
The FRR and FAR values ​​are for the Palm Vein scanner. According to the developer at FAR 0.0008% FRR is 0.01%. No company produces a more accurate schedule for several values.

Advantages and disadvantages of the method

Advantages of the method. No need to contact the scanning device. High reliability - the statistical indicators of the method are comparable with the readings of the iris. Hidden characteristics: unlike all of the above, it is very difficult to obtain this characteristic from a person “on the street”, for example, by photographing him with a camera.
Disadvantages of the method. Exposure of the scanner to sunlight and rays of halogen lamps is unacceptable. Some age-related diseases, such as arthritis, greatly impair FAR and FRR. The method is less studied in comparison with other static biometric methods.

Market situation

Hand vein recognition is a fairly new technology, and therefore its global market share is small, around 3%. However, there is growing interest in this method. The fact is that, being quite accurate, this method does not require such expensive equipment as, for example, recognition methods based on facial geometry or the iris. Now many companies are developing in this area. So, for example, by order of the English company TDSi, software was developed for the palm vein biometric reader PalmVein, presented by Fujitsu. The scanner itself was developed by Fujitsu primarily to combat financial fraud in Japan.
Also in the field of vein identification are the following companies Veid Pte. Ltd. (scanner, software), Hitachi VeinID (scanners)
I don't know any companies in Russia dealing with this technology.

Retina

Until recently, it was believed that the most reliable method of biometric identification and authentication of a person is a method based on scanning the retina. It contains the best features of identification by the iris and by the veins of the hand. The scanner reads the pattern of capillaries on the surface of the retina. The retina has a fixed structure that does not change over time, except as a result of a disease, such as cataracts.
Retinal scanning uses low-intensity infrared light directed through the pupil to the blood vessels at the back of the eye. Retinal scanners have become widely used in access control systems for highly secret objects, as they have one of the lowest percentages of denied access to registered users and there are practically no erroneous access permissions.
Unfortunately, a number of difficulties arise when using this biometric method. The scanner here is a very complex optical system, and a person must not move for a considerable time while the system is induced, which causes discomfort.
According to EyeDentify for the ICAM2001 scanner with FAR=0.001%, the FRR value is 0.4%.

Advantages and disadvantages of the method

Advantages. High level of statistical reliability. Due to the low prevalence of systems, there is little chance of developing a way to "cheat" them.
Flaws. Difficult to use system with high processing time. The high cost of the system. The lack of a wide market offer and, as a result, the insufficient intensity of the development of the method.

Hand geometry

This method, quite common 10 years ago, and originating from forensic science, has been declining in recent years. It is based on obtaining the geometric characteristics of the hands: the length of the fingers, the width of the palm, etc. This method, like the retina of the eye, is dying, and since it has much lower characteristics, we will not even enter a more complete description of it.
It is sometimes believed that geometric recognition methods are used in vein recognition systems. But in the sale, we have never seen such a clearly stated. And besides, often when recognizing by veins, only the palm of the hand is taken, while when recognizing by geometry, a picture is taken of the fingers.

A little self-promotion

At one time, we developed a good eye recognition algorithm. But at that time, such a high-tech thing was not needed in this country, and I did not want to go to the bourgeoisie (where we were invited after the very first article). But suddenly, after a year and a half, there were still investors who wanted to build a “biometric portal” for themselves - a system that would eat 2 eyes and use the color component of the iris (for which the investor had a world patent). In fact, this is what we are doing now. But this is not an article about self-promotion, this is a brief lyrical digression. If anyone is interested, there is some information, and sometime in the future, when we enter the market (or do not), I will write a few words here about the ups and downs of the biometric project in Russia.

findings

Even in the class of static biometric systems, there is a large selection of systems. Which one to choose? It all depends on the security requirements. The most statistically reliable and tamper-resistant access systems are iris and arm vein access systems. For the first of them, there is a wider market for proposals. But this is not the limit. Biometric identification systems can be combined to achieve astronomical accuracy. The cheapest and easiest to use, but with good statistics, are finger-tolerance systems. 2D face tolerance is convenient and cheap, but has a limited scope due to poor statistics.
Consider the characteristics that each of the systems will have: resistance to forgery, resistance to the environment, ease of use, cost, speed, stability of the biometric feature over time. Let's place marks from 1 to 10 in each column. The closer the score is to 10, the better the system is in this regard. The principles for choosing grades were described at the very beginning of the article.


We also consider the ratio of FAR and FRR for these systems. This ratio determines the efficiency of the system and the breadth of its use.


It is worth remembering that for the iris, you can increase the accuracy of the system almost quadratically, without loss of time, if you complicate the system by making it for two eyes. For the fingerprint method - by combining several fingers, and recognition by veins, by combining two hands, but such an improvement is possible only with an increase in the time spent working with a person.
Summarizing the results for the methods, we can say that for medium and large objects, as well as for objects with a maximum security requirement, the iris should be used as a biometric access and, possibly, recognition by hand veins. For facilities with up to several hundred employees, fingerprint access will be optimal. 2D facial recognition systems are very specific. They may be required in cases where recognition requires the absence of physical contact, but it is not possible to place the control system on the iris. For example, if it is necessary to identify a person without his participation, with a hidden camera, or an outdoor detection camera, but this is possible only with a small number of subjects in the database and a small flow of people filmed by the camera.

Young technicians take note

Some manufacturers, such as Neurotechnology, have demo versions of the biometric methods they release on their website, so you can plug them in and play around. For those who decide to delve into the problem more seriously, I can advise the only book that I have seen in Russian - "A Guide to Biometrics" by R.M. Ball, J.H. Connell, S. Pancanti. There are many algorithms and their mathematical models. Not everything is complete and not everything corresponds to the present, but the base is not bad and comprehensive.

P.S.

In this opus, I did not go into the problem of authentication, but only touched on identification. In principle, from the characteristics of FAR / FRR and the possibility of forgery, all conclusions on the issue of authentication suggest themselves.

Tags:

• biometrics
• fingerprint scanners

Add tags

Vitaly Zadorozhny

PC Magazine/Russian Edition №1, 2004

Introduction

Fingerprint identification is by far the most common biometric technology. According to the International Biometric Group, the share of fingerprint recognition systems is 52% of all biometric systems used in the world, and according to forecasts, sales of such systems in 2003 alone will be approximately $ 500 million, with a tendency to double this amount every year.

It is difficult to say exactly when fingerprints were used for identification. Archaeologists during excavations quite often come across certain images of fingerprints on a stone, but it cannot be argued that they were used for identification. In addition, on the other hand, it is known for certain that in Ancient Babylon and China, fingerprints were made on clay tablets and seals, and in the 14th century in Persia, various state documents were “signed” with fingerprints. This suggests that it was already noted at that time: a fingerprint is a unique characteristic of a person by which he can be identified.

The next stage in the development of technology is the beginning of its use in forensic science, by the middle of the 19th century, the first assumptions were made about the uniqueness of the fingerprints of each person and attempts were made to classify them according to different parts of the papillary pattern. All this led to the appearance in 1897 (according to some sources, 1899) of the "Henry system", the first widespread classification of fingerprints, developed by the Englishman Edward Henry during his stay in India. By the end of the 19th century, the first algorithms for comparing fingerprints appeared. Over the next 25 years, the "Henry system" was adapted for use at the state level in various countries, and from about 1925 began to be widely used in forensic science around the world.

However, despite the widespread use of fingerprint recognition techniques for human identification, primarily in forensic science, it has not yet been scientifically proven that the pattern of a human finger papillary pattern is an absolutely unique characteristic. And although in the entire more than a century-long history of using this technology in forensics and other areas, there has not been a situation when there would be two people with exactly the same fingerprints (we do not take into account errors in software and hardware implementations of recognition algorithms), the uniqueness of fingerprints is still empirical observation.

Although, perhaps, this is the very case when the unprovenness of the hypothesis does not indicate that it is false, but that it is extremely difficult to prove.

In the second half of the 20th century, due to the emergence of new technical capabilities, fingerprint recognition began to go beyond the scope of use only in forensics and found its application in various areas of information technology; First of all, these areas were:

• access control systems;
• information security (network access, PC login);
• accounting of working hours and registration of visitors;
• voting systems;
• making electronic payments;
• authentication on Web resources;
• various social projects where identification of people is required (charity events, etc.);
• civil identification projects (crossing state borders, issuing visas to visit the country, etc.).

Let us dwell in more detail on the internal aspects of the operation of modern biometric fingerprint recognition systems, on how their work begins and what is the core of any such system.

In the first part of the article, methods for obtaining a fingerprint in electronic form, in other words, types of scanners and methods for scanning fingers, will be considered.

In the second part of the article, the main methods of fingerprint recognition, algorithms for building recognition systems and some methods of protection against dummies will be disclosed.

Fingerprint scanning

Obtaining an electronic representation of fingerprints with a well-defined papillary pattern is a rather difficult task. Since the fingerprint is too small, it is necessary to use quite sophisticated methods to obtain a high-quality image of it.

All existing fingerprint scanners can be divided into three groups according to the physical principles they use:

• optical;
• silicon;
• ultrasonic.

Let's consider each of them, point out their advantages and disadvantages, as well as the leading manufacturers (sometimes the only ones) involved in the implementation of each of the methods.

Optical scanners- are based on the use of optical imaging methods. Currently, there are the following technologies for the implementation of optical scanners:

1. FTIR Scanners - are devices that use the effect of frustrated total internal reflection (Frustrated Total Internal Reflection, FTIR). Let us consider this effect in more detail in order to explain the full algorithm of the operation of such scanners.

When light falls on the interface between two media, the light energy is divided into two parts: one is reflected from the interface, the other penetrates through the interface into the second medium. The fraction of reflected energy depends on the angle of incidence. Starting from a certain value, all light energy is reflected from the interface. This phenomenon is called total internal reflection. However, upon contact of a denser optical medium (in our case, the surface of a finger) with a less dense one (in practical implementation, as a rule, the surface of a prism) at the point of total internal reflection, the light beam passes through this boundary. Thus, only beams of light that hit such points of total internal reflection, to which the grooves of the papillary pattern of the finger surface were not applied, will be reflected from the boundary. A special camera (CCD or CMOS, depending on the implementation of the scanner) is used to fix the resulting light image of the finger surface.

Leading manufacturers of this type of scanners: BioLink, Digital Persona, Identix.

2. fiber optic scanners (fiber optic scanners) - are a fiber optic matrix, each of the fibers of which ends with a photocell. The sensitivity of each photocell makes it possible to fix the residual light passing through the finger at the point where the finger relief touches the scanner surface. The fingerprint image is formed according to the data of each of the elements.

The leading manufacturer of scanners of this type is Delsy.

3. Electro-optical scanners (electro-optical scanners) - this technology is based on the use of a special electro-optical polymer, which includes a light-emitting layer. When a finger is applied to the scanner, the inhomogeneity of the electric field near its surface (the potential difference between the tubercles and depressions) is reflected in the glow of this layer so that it highlights the fingerprint. The scanner's photodiode array then converts this glow into digital form.

The leading manufacturer of this type of scanners is Security First Corp (Ethentica).

4. Optical traction scanners (sweep optical scanners) are generally similar to FTIR devices. Their peculiarity is that the finger must not only be applied to the scanner, but carried out along a narrow strip - the reader. When you move your finger across the surface of the scanner, a series of snapshots (frames) is taken. At the same time, adjacent frames are taken with some overlap, i.e. they overlap each other, which makes it possible to significantly reduce the size of the prism used and the scanner itself. Specialized software is used to form (more precisely, assemble) a fingerprint image as it moves along the scanning surface.

The leading manufacturer of this type of scanners is Kinetic Sciences.

5. Roller scanners (roller-style scanners) - in these miniature devices, finger scanning occurs when a transparent thin-walled rotating cylinder (roller) is rolled with a finger. During the movement of the finger along the surface of the roller, a series of snapshots (frames) of a fragment of the papillary pattern in contact with the surface is taken. Similar to a rolling scanner, adjacent frames are superimposed, which makes it possible to collect a complete fingerprint image without distortion. When scanning, the simplest optical technology is used: inside a transparent cylindrical roller there is a static light source, a lens and a miniature camera. The image of the illuminated area of ​​the finger is focused by the lens on the sensitive element of the camera. After a complete “scrolling” of the finger, a “picture” of his fingerprint is “collected”.

Leading manufacturers of this type of scanners: Digital Persona, CASIO Computer, ALPS Electric.

6. Non-contact scanners (touchless scanners) - they do not require direct contact of the finger with the surface of the scanning device. The finger is applied to the hole in the scanner, several light sources illuminate it from below from different sides, in the center of the scanner there is a lens through which the collected information is projected onto a CMOS camera that converts the received data into a fingerprint image.

The leading manufacturer of scanners of this type is Touchless Sensor Technology.

Let's note several historical shortcomings of optical scanners and indicate which of them have already been corrected:

• the impossibility of making them compact, however, as can be seen from the above four of the six figures, this is currently possible;
• optical modules are quite expensive due to the large number of components and the complex optical system. And this problem has now been solved: the price of optical sensors from some manufacturers is now $10-$15 (not to be confused with the price of a sensor in an end-user package complete with software);
• optical scanners are not resistant to dummies and dead fingers. The next part of the article will be devoted to this issue, but already now it is worth noting that almost all manufacturers have implemented mechanisms for protecting against dummies at one stage or another of processing a scanned image.

Semiconductor Scanners- they are based on the use of semiconductor properties to obtain an image of the finger surface, which change at the points of contact of the ridges of the papillary pattern with the scanner surface. Currently, there are several technologies for the implementation of semiconductor scanners.

1. Capacitive Scanners (capacitive scanners) - the most widespread type of semiconductor scanners, in which to obtain a fingerprint image, the effect of changing the capacitance of the pn-junction of a semiconductor device when the ridge of the papillary pattern comes into contact with an element of the semiconductor matrix is ​​\u200b\u200bused. There are modifications of the described scanner, in which each semiconductor element in the scanner matrix acts as one capacitor plate, and the finger acts as another. When a finger is applied to the sensor, a certain capacitance is formed between each sensitive element and the protrusion-cavity of the papillary pattern, the value of which is determined by the distance between the surface of the finger and the element. The matrix of these containers is converted into a fingerprint image.

Leading manufacturers of this type of scanners: Infineon, ST-Microelectronics, Veridicom.

2. Pressure sensitive scanners (pressure scanners) - these devices use sensors consisting of a matrix of piezoelectric elements. When a finger is applied to a scanning surface, the protrusions of the papillary pattern exert pressure on a subset of the surface elements, respectively, the depressions do not exert any pressure. The matrix of stresses obtained from the piezoelectric elements is converted into an image of the finger surface.

Leading manufacturer of this type of scanner: BMF.

3. Thermal Scanners (thermal scanners) - they use sensors that consist of pyroelectric elements that allow you to capture the temperature difference and convert it into voltage (this effect is also used in infrared cameras). When a finger is applied to the sensor, based on the temperature of the protrusions of the papillary pattern touching the pyroelectric elements and the temperature of the air in the depressions, a temperature map of the finger surface is built and converted into a digital image.

Generally speaking, in all the above semiconductor scanners, a matrix of sensitive microelements (the type of which is determined by the method of implementation) and a converter of their signals into digital form are used. Thus, a generalized scheme of operation of the above semiconductor scanners can be demonstrated as follows. (See picture.)

The most common (“classic”) types of semiconductor scanners have been described above, then we will consider other, less common types.

4. RF Scanners (RF-Field scanners) - these scanners use a matrix of elements, each of which works like a small antenna. The sensor generates a weak radio signal and sends it to the scanned surface of the finger, each of the sensitive elements receives a signal reflected from the papillary pattern. The value of the EMF induced in each microantenna depends on the presence or absence of a papillary pattern in the vicinity of the crest. The stress matrix thus obtained is converted into a digital fingerprint image.

Leading manufacturer of this type of scanner: Authentec.

5. Stretch thermo-scanners (thermal sweep scanners) - a kind of thermal scanners that use, as in optical sweep scanners, swiping a finger over the surface of the scanner, and not just applying it.

Leading scanner manufacturer of this type: Atmel.

6. Capacitive traction scanners (capacitive sweep scanners) - use a similar method of frame-by-frame assembly of a fingerprint image, but each frame of the image is obtained using a capacitive semiconductor sensor.

Leading manufacturers of this type of scanners: Fujitsu.

7. RF traction scanners (RF-Field sweep scanners) - similar to capacitive, but using radio frequency technology.

Produces scanners of this type: Authentec.

Let us note the main disadvantages of semiconductor scanners, although they are not typical for all the described methods:

• scanners, in particular those sensitive to pressure, give an image of low resolution and small size;
• the need to apply a finger directly to the semiconductor surface (since any intermediate layer affects the scanning results) leads to its rapid wear;
• sensitivity to strong external electric fields that can cause electrostatic discharges that can disable the sensor (applies primarily to capacitive scanners);
• a large dependence of image quality on the speed of movement of the finger along the scanning surface is inherent in rolling scanners.

Ultrasonic scanners- this group is currently represented by only one scanning method, which is called so.

Ultrasound Scan - this is scanning the surface of the finger with ultrasonic waves and measuring the distance between the wave source and the depressions and protrusions on the surface of the finger by echo reflected from them. The quality of the image obtained in this way is 10 times better than that obtained by any other biometric method on the market. In addition, it should be noted that this method is almost completely protected from dummies, since it allows, in addition to a fingerprint, to obtain some additional characteristics about its condition (for example, the pulse inside the finger).

The leading manufacturer of scanners of this type is Ultra-Scan Corporation (UCS).

The main disadvantages of ultrasonic scanners are:

• high price compared to optical and semiconductor scanners;
• large size of the scanner itself.

Otherwise, we can safely say that ultrasonic scanning combines the best characteristics of optical and semiconductor technologies.

Summing up the above, I would like to note the rapid growth in the number of fingerprint scanning methods. Until recently, there were only two technologies: optical FTIR and semiconductor capacitance with their own stable advantages and disadvantages. However, over the past ten years, recognition technology has developed so much that the latest generation of scanners not only overcome almost all of their old shortcomings, but also acquired a number of particularly attractive features, such as extremely small size and low price. In addition, a fundamentally new ultrasound scanning technology has appeared, which has yet to go through all the stages of formation. But even now we can talk about its enormous potential.