Modern science does not stand still. Increasingly, quality protection is required for devices, so that those who accidentally take possession of them can not make full use of the information. In addition, methods of protecting information from unauthorized access are used not only in everyday life.
In addition to entering passwords in digital form, more individualized biometric protection systems are used.
What it is?
Previously, such a system was used only in limited cases, to protect the most important strategic objects.
Then, after September 11, 2011, came to the conclusion that such a way of protecting information and access can be applied not only in these areas, but also in other areas.
Thus, the methods of identifying a person have become indispensable in a number of methods to combat fraud and terrorism, as well as in such areas as:
- biometric systems of access to communication technologies, network and computer databases;
- control access to the information store, etc.
Each person has a set of characteristics that do not change with time, or those that can be modified, but at the same time belong only to a specific person. In this regard, we can distinguish the following parameters of biometric systems that are used in these technologies:
- dynamic - features of handwriting, voice, etc .;
- static - fingerprints, photographing the auricles, scanning the retina of the eye and others.
Biometrics technologies in the future will replace the usual methods of authenticating a person under a passport, since embedded chips, maps and similar innovations of scientific technologies will be implemented not only in this document, but also in others.
A small digression about the ways of personality recognition:
- Identification - one to many; The sample is compared with all available for certain parameters.
- Authentication - one to one; The sample is compared with the previously obtained material. In this case, the person may be aware that the received person's data are compared with the sample of the person's parameter in the database;
How Biometric Protection Systems Work
In order to create a base for a particular person, it is necessary to consider its biological individual parameters as a special device.
The system remembers the obtained sample of the biometric characteristic (the recording process). In this case, it may be necessary to make several samples to compile a more accurate control value of the parameter. The information received by the system is transformed into a mathematical code.
In addition to creating a sample, the system can request additional actions in order to combine a personal identifier (PIN or smart card) and a biometric sample. In the future, when a scan is made for compliance, the system compares the obtained data by comparing the mathematical code with those already recorded. If they match, this means that the authentication was successful.
The system can give out errors, unlike recognition by passwords or electronic keys. In this case, the following types of incorrect information are distinguished:
- type 1 error: false access rate (FAR) - one person can be mistaken for another;
- Error of the 2nd kind: the coefficient of false access denial (FRR) - the person is not recognized in the system.
In order to exclude, for example, errors of this level, it is necessary to cross the FAR and FRR indices. However, this is impossible, because for this it would be necessary to carry out identification of a person by DNA.
At the moment, the most known method of biometrics. When obtaining a passport, modern citizens of Russia must undergo the procedure of fingerprinting for entering them into a personal card.
This method is based on the uniqueness of the papillary finger pattern and has been used for quite a long time, beginning with criminology (dactyloscopy). Scanning the fingers, the system translates the sample into a kind of code that is then compared with the existing identifier.
Typically, information processing algorithms use the individual location of certain points, which contain fingerprints-forkings, the end of the pattern line, etc. The time that takes the translation of the image into the code and the output of the result is usually about 1 second.
The equipment, including the software for it, is produced at the moment in the complex and is relatively inexpensive.
The occurrence of errors when scanning the fingers of the hand (or both hands) occurs quite often in the following cases:
- There is unusual humidity or dry fingers.
- Hands are treated with chemical elements that make identification difficult.
- There are microcracks or scratches.
- There is a large and continuous flow of information. For example, it is possible in an enterprise where access to the workplace is carried out using a fingerprint. Since the flow of people is considerable, the system can fail.
The most famous companies that deal with fingerprint recognition systems are: Bayometric Inc., SecuGen. In Russia, work on this: "Sonda", BioLink, "SmartLoc", etc.
The envelope pattern is formed at the 36th week of intrauterine development, it is set to two months and does not change during life. Biometric iris identification systems are not only the most accurate among others in this series, but also one of the most expensive.
The advantage of the method is that scanning, i.e. image capture, can occur both at a distance of 10 cm, and at a 10-meter distance.
When the image is locked, data about the location of certain points on the iris of the eye are transmitted to the calculator, which then gives information about the possibility of tolerance. The speed of processing information about the iris of a person is about 500 ms.
At the moment, this recognition system on the biometric market occupies no more than 9% of the total number of such identification methods. At the same time , the market share occupied by fingerprint technology is more than 50%.
Scanners that allow you to capture and process the iris of the eye have a rather complex design and software, and therefore a high price is set for such devices. In addition, Iridian was the monopolist in the production of iris recognition systems. Then other large companies began to enter the market, which already were engaged in the production of components of various devices.
Thus, at the moment in Russia there are the following companies that form systems for recognizing a person by the iris of the eye: AOptix, SRI International. However, these firms do not provide indicators for the number of errors of 1 and 2 kinds, so it is not a fact that the system is not protected against forgery.
Geometry of the face
There are biometric security systems associated with face recognition in 2D and 3D modes. In general, it is believed that the features of each person's face are unique and do not change during life. The characteristics such as the distances between certain points, the shape, etc., remain unchanged.
2D mode is a static method of identification. When fixing an image, it is necessary that the person does not move. The background, the presence of the mustache, the beard, the bright light and other factors that prevent the system from recognizing the face also have significance. This means that for any inaccuracies, the result will be incorrect.
At the moment, this method is not very popular because of its low accuracy and is used only in multimodal (cross) biometrics, which is a combination of ways of recognizing a person by face and voice simultaneously. Biometric protection systems can include other modules - DNA, fingerprints and others. In addition, the cross method does not require contact with a person who needs to be identified, which makes it possible to recognize people by photos and voice recorded on technical devices.
The 3D method has completely different input parameters, so it can not be compared with 2D technology. When recording an image, the person is used in dynamics. The system, fixing each image, creates a 3D model, which then compares the obtained data.
In this case, a special grid is used that is projected onto the person's face. Biometric security systems, making several frames per second, process the image of the software included in them. At the first stage of creating a software image, discard unsuitable images where the face is difficult to see or there are secondary objects.
Then the program determines and ignores unnecessary items (glasses, hairstyle, etc.). Anthropometric features of the face are allocated and remembered, generating a unique code that is stored in a special data store. The image capture time is about 2 seconds.
However, despite the advantage of the 3D method over the 2D method, any significant interference on the face or a change in facial expression worsen the statistical reliability of this technology.
To date, biometric face recognition technologies have been used along with the best-known methods described above, accounting for approximately 20% of the entire biometric technology market.
Companies that develop and implement face detection technology: Geometrix, Inc., Bioscrypt, Cognitec Systems GmbH. In Russia, the following firms work on this issue: Artec Group, Vocord (2D-method) and other smaller manufacturers.
About 10-15 years ago a new technology of biometric identification came - recognition by the veins of the hand. This became possible due to the fact that hemoglobin, which is in the blood, intensively absorbs infrared radiation.
A special IR camera takes a picture of the palm, which results in a grid of veins in the image. This image is processed by the software, and the result is output.
The arrangement of veins on the arm is comparable to the peculiarities of the iris of the eye - their lines and structure do not change with time. The reliability of this method can also be correlated with the results obtained by identification with the iris.
You do not need to contact to capture an image with a reader, but using this method requires certain conditions under which the result will be most accurate: you can not get it if, for example, you photograph the hand on the street. Also, during scanning, the camera can not be illuminated. The end result will be inaccurate if there are age-related diseases.
The spread of the method on the market is only about 5%, but it attracts great interest from large companies that have already developed biometric technologies: TDSi, Veid Pte. Ltd., Hitachi VeinID.
Scanning the pattern of capillaries on the surface of the retina is considered the most reliable method of identification. It combines the best characteristics of biometric technologies for human recognition by the iris of the eyes and the veins of the hand.
The only time the method can give inaccurate results is cataract. In general, the retina has an unchanging structure throughout life.
The minus of this system is that the scan of the retina is made when the person does not move. Difficult in its application technology provides a long processing time.
Because of the high cost, the biometric system does not have enough distribution, but it gives the most accurate results from all the methods of scanning human features offered on the market.
Previously, the popular method of hand geometry identification is becoming less applicable, since it gives the lowest results in comparison with other methods. When scanning, fingers are photographed, their length, the relationship between nodes and other individual parameters are determined.
The shape of the ears
Experts say that all existing methods of identification are not as accurate as recognizing a person in the shape of the ear. However, there is a way to determine the identity of the DNA, but in this case, there is close contact with people, so it is considered unethical.
Researcher Mark Nixon from the UK says that the methods of this level are biometric systems of the new generation, they yield the most accurate results. In contrast to the retina, iris or fingers, which can be very likely to appear extraneous parameters that make identification difficult, this does not happen on the ears. Formed in childhood, the ear only grows, not changing at its main points.
The inventor called the method of human identification by the organ of hearing the "beam image transformation". This technology involves capturing images with rays of different colors, which is then translated into mathematical code.
However, according to the scientist, his method also has negative sides. For example, the hair that closes the ears, mistakenly selected foreshortening and other inaccuracies can interfere with obtaining a clear image.
Ear scanning technology does not replace such a familiar and familiar way of identification as fingerprints, but can be used along with it.
It is believed that this will increase the reliability of human recognition. Particularly important is the combination of different methods (multimodal) in capturing criminals, the scientist believes. As a result of experiments and research, they hope to create software that will be used in court to uniquely identify the perpetrators of the image.
The Voice of Man
Identification of identity can be conducted both locally and remotely, using voice recognition technology.
When talking, for example, by phone, the system compares this parameter with those available in the database and finds similar patterns in percentage terms. Full coincidence means that the identity is established, that is, there was an identification by voice.
In order to gain access to something in the traditional way, it is necessary to answer certain security questions. This is a digital code, mother's maiden name and other text passwords.
Modern research in this field shows that this information is fairly easy to acquire, so that identification methods such as voice biometrics can be used. In this verification is not the knowledge of codes, but the identity of a person.
For this, the client needs to pronounce a code phrase or start talking. The system recognizes the caller's voice and checks whether it is a member of that person - whether he is who he claims to be.
Biometric systems of information protection of this type do not require expensive equipment, this is their advantage. In addition, to conduct voice scanning system does not need to have special knowledge, since the device independently produces the result of the type of "true - false".
However, the voice can change either with age or due to illness, so the method is reliable only when everything is in order with this parameter. The accuracy of the results can also be affected by extraneous noise.
Identification of a person by the method of writing letters takes place practically in any sphere of life, where it is necessary to put a signature. This happens, for example, in a bank, when a specialist compares a sample formed when opening an account, with signatures affixed to the next visit.
The accuracy of this method is not high, since identification does not occur with the help of mathematical code, as in the previous ones, but by simple comparison. The level of subjective perception is high here. In addition, the handwriting changes with age, which often makes recognition difficult.
It is better in this case to use automatic systems that will allow us to determine not only visible coincidences, but also other distinguishing features of spelling words, such as slope, distance between points and other characteristic features.