Introduction of several common biometric technologies

Several common biometric analysis techniques include fingerprints, palm-shaped, finger veins, retina, iris, face recognition techniques...

Fingerprints <br><br> Fingerprints are strips of lines on human fingers. Their formation depends on the environment in which the embryo is developing. At present, many countries use fingerprints as personal information collected by the government to store them in an identity database and become a means for the identification of the judicial department.

As the most traditional and mature biometric identification technology, fingerprints have the following two prominent advantages: stability, from the complete formation of the fetus at 6 months to the death of the body after the death of the human body, fingerprint line type, structure, statistical characteristics There is no obvious change in the overall distribution, etc.; uniqueness. To date, no two fingerprints are identical.

Fingerprint comparisons are usually identified using the feature point method, extracting the divergence of the convex curve on the fingerprint or the part (endpoint) in the fingerprint. In recent years, with the development of electronic technology, the performance of automatic fingerprint recognition has been greatly improved. Under normal circumstances, recognition generally takes only about 1 second, the rate of false rejection is less than 2%, and the incidence of false acceptance is less than 0.0001%.

However, in order to improve the reliability, there is a certain requirement for the placement position of the fingerprint identification device for the opponent. In addition, the system also has certain requirements on the actual situation of the finger, and the recognition rate of the dirty finger or the dry finger will be reduced.

For end-users, because fingerprints are currently entered as personal information in official identification databases in many places, they are used in access control systems. If mis-management occurs, there is a risk of leakage of personal information.

Hand shape

Hand shape recognition is a technique that emerged in the 1980s. The device for identifying hand shape is based on the three-dimensional measurement of the geometry of the human hand. Because each person's hand is different, it can be used as a condition for recognition. The recognition function is mainly achieved by determining several external features of the human hand, including the length, width, thickness and surface area of ​​the palm, the width of the fingers at different positions, the length of the fingers, the thickness of the fingers, and the curvature of the curved portion of the fingers. These data provide a unique combination of relationships to ensure rapid, accurate, and reliable identification.

Normally, the rate of false rejects for hand recognition devices is approximately 0.03%, and the incidence of false acceptance is 0.1%. It takes only one second for the system to complete a recognition.

Finger vein

Finger vein recognition is a technique that uses near-infrared light to irradiate a living human finger vein and acquires, encodes, and authenticates a vein image. Medical research proves that the shape of human finger veins is unique and stable, that is, each person's finger vein image is not the same, and the vein images of the same person's different fingers are not the same; the vein shapes of healthy adults no longer change. This provides a medical basis for finger vein identification. Compared with fingerprint recognition technology, it is hidden inside the body and requires living finger veins, so the chance of being copied or stolen is very small. The subject's psychological resistance is low, affected by physical and environmental factors, and overcome the dry skin , oil, dust, skin surface anomalies and other factors, the original vein image from capture to digital processing, the entire process is less than 1 second, and has a high accuracy rate that can trigger (false rejection rate is about 0.01%, false acceptance occurs The rate is about 0.0001%) and many other important features make it far better than fingerprint recognition technology in terms of high security and ease of use.

Retinal <br> <br> retina recognition principle is distinguished by analyzing each blood vessel pattern on the retina. The retinal scan uses low-intensity infrared light to illuminate the retina to capture images of major blood vessels. Since the retina is behind the eyeball, the acquisition process requires a high degree of user coordination to ensure correct illumination and alignment of the retina, and requires standing 2-3 feet to remain stationary for 1-2 seconds. What's more important is the identifi- ers’ concerns about retinal scanning technology, and fears that it will affect eye health. For these reasons, retina recognition technology has not become a mainstream technology in biometrics.

The iris is an annular iris color <br> <br> tissue surrounding the pupil, it is rich and varied texture patterns, forms the basis for iris recognition. The formation of the iris is determined by genetics, and the human gene expression determines the morphology, physiology, color and overall appearance of the iris. By the age of two, the iris has basically developed enough size to enter a relatively stable period. In addition to rare abnormal conditions, physical or mental trauma caused by changes in the appearance of the iris, the iris morphology can remain unchanged in decades, in addition, because the iris has a transparent cornea external to the outside world Isolated, therefore, the fully developed iris is not vulnerable to external damage and changes. The iris recognition technology scans and images the iris pattern through an approximate infrared light, and determines the degree of similarity through the exclusive OR operation of the pixel positions of the pattern. The iris recognition process first needs to separate the iris from the eye image and then perform the feature analysis. Theoretically, the probability of finding two identical irises is 1.2 million, which is also the most accurate of all known biometric technologies. of.

Iris recognition cannot be widely used in the civilian market because of complicated equipment, short scanning distances, and users' psychological concerns.

Facial <br> <br> face recognition is a biological identification technology identification based on facial features of people's information. The camera captures images or video streams containing faces and automatically detects and tracks the faces in the images, and then takes a series of related technical measures on the detected face images, including face image collection, face positioning, and human faces. Recognition preprocessing, memory storage and comparison identification, to achieve the purpose of identifying different people.

Facial recognition devices mainly analyze face shapes and features, including the outline, shape, and position of the eyes, nose, mouth, eyebrows, and faces. Face recognition is very complicated due to the difference in brightness and angles and facial expressions. In addition, the facial recognition system is very sensitive to direct light exposure, especially sunlight. In this case, the false rejection rate will increase greatly. In some cases, it may not even be possible to identify.