Biometric system

Due to the uniqueness of the human body that cannot be copied, the biological key cannot be copied, stolen or forgotten. The stage is from mechanical keys to digital keys such as passwords or bar codes. Biometrics is the highest level security key system in today's digital life.

Biometrics technology uses people's physiological or behavioral characteristics to check or confirm people's identities. Nowadays, the use of biometric technology has developed rapidly, and it has continuously entered into many application fields. It has been widely used in physical security (access control, building monitoring) and logical security (computer, network). Keda Information Technology Co., Ltd. has mastered a lot of biometrics in long-term cooperation with top scientific research institutions and enterprises at home and abroad, which can provide customers with: true convenience and safety.

The following is a general introduction to biometrics.

Biometric technology is a solution that relies on the physical characteristics of the human body for identity verification. The biological characteristics of the human body include fingerprints, sounds, faces, retinas, palm prints, skeletons and so on. The core of the so-called biometrics lies in how to obtain these biometrics, convert them into digital information, store them in a computer, and use reliable matching algorithms to complete the process of verifying and identifying personal identities.

Due to the uniqueness of the human body that cannot be copied, the biological key cannot be copied, stolen or forgotten. However, common passwords, IC cards, striped codes, magnetic cards or keys have many disadvantages such as loss, forgetting, copying and theft. Therefore, using biological "keys", you don't have to carry a large series of keys, and you don't have to bother to remember or change the password. And system administrators do not have to be helpless because they have forgotten their passwords.

Humans have experienced three stages of development in the effectiveness and convenience of tracking documents, transactions, and the security of articles. The first stage, which is the initial method, is to use various mechanical keys that everyone is already familiar with. The second stage is to develop from mechanical keys to digital keys such as passwords or bar codes. The third stage is to use the inherent biological characteristics of the human body to identify and verify identity. Biometrics is the highest level security key system in today's digital life.

fingerprint

At the beginning of the nineteenth century, scientific research discovered two important features that are still recognized today: one is that the patterns of the fingerprint ridges of two different fingers are different, and the other is that the pattern of the fingerprint ridges remains unchanged for life. This research result makes fingerprints formally used in criminal identification. In the 1960s, because computers could effectively process graphics, people began to study computers to process fingerprints. The research and application of automatic fingerprint recognition system AFIS in law enforcement began.

An excellent biometric system requires that it can quickly and effectively complete its identification process. All biometric systems include the following processes: acquisition, decoding, comparison and matching. Fingerprint recognition processing is the same, it includes fingerprint image collection, fingerprint image processing feature extraction, feature value comparison and matching and other processes. The advantage of using fingerprint identification is that it is reliable, convenient and easy to be accepted. You only need to spend insignificant time to obtain fingerprint images with a fingerprint device. Many studies have shown that fingerprint recognition is the least intrusive technology in all biometric technologies.

Palm print

Palm geometry is based on the fact that the shape of almost everyone's hand is different, and that the shape of this hand no longer changes significantly after a person reaches a certain age. When the user places his hand on the hand-shaped reader, the three-dimensional image of a hand is captured. Next, measure the shape and length of the fingers and knuckles.

According to the different data used to identify people, hand shape reading technology can be divided into the following three categories: palm application, the pattern of blood vessels in the hand, and geometric analysis of fingers. Mapping the different features of the shot is quite simple and does not generate a large number of data sets. However, even with a considerable number of records, palm geometry may not be able to distinguish people, because the characteristics of the hands are very similar. Compared with other biometric methods, palm geometry cannot achieve the highest degree of accuracy. When the database continues to increase, it is necessary to increase the number of obvious characteristics of the hand to clearly identify and compare people and templates.

Retina

Biometric technology that analyzes the complex and unique characteristics of the eye is divided into two different areas: iris recognition technology and corneal recognition technology.

The iris is a layer of colored cellular tissue surrounding the pupil. The iris recognition system uses a camera to capture the sample, and then the software compares the obtained data with the stored template.

The cornea is the layer of blood cells at the bottom of the eye. Corneal scanning is performed using low-density infrared to capture the unique characteristics of the cornea. As far as we know, the area in the center of the cornea is scanned, and the only pattern of blood cells is captured. Corneal identification technology is considered to be the best biometric. However, despite its high degree of accuracy, people often think this technology is inconvenient. Therefore, it is difficult to gain universal acceptance by end users. The corneal scanner requires the subject to stand upright while it reads corneal information.

Eye and corneal scanners are ineffective for blind people and people with eyes.

face

The face recognition system recognizes people by analyzing the unique shapes, patterns and positions of facial features. There are basically two ways to process data: camera and heat mapping. Standard camera technology is based on facial images captured by the camera. Thermal mapping technology analyzes the heat generation pattern of blood vessels under the skin. The appeal of this biometric technology is its human-computer interaction.

However, this system is very unreliable and expensive. For example, it cannot distinguish between twins or triplets, the user who finished the haircut, or the same person wearing glasses and not wearing glasses.

sound

Voice recognition is the use of the speaker's voice and linguistic patterns based on physiological and behavioral characteristics. It differs from language recognition in that this technology does not recognize the spoken words themselves. But by analyzing the unique characteristics of speech, such as the frequency of pronunciation, to identify the person speaking. Speech recognition technology allows people to control whether they can enter or exit restricted areas through their voices. For example, dialing into a bank, database service, shopping or voice mail by phone, and entering a secret device.

Although voice recognition is convenient, it is not reliable due to the risk of dehumanization, remote control, and low accuracy. A person suffering from a cold may be falsely rejected and thus unable to use the speech recognition system.

signature

Signature recognition, also known as signature mechanics identification (Danamic Signature Verification--DSV), is based on the strength of the signature. It analyzes the movement of the pen, such as acceleration, pressure, direction, and length of the stroke, not the image of the signature itself. The key to signature mechanics is to distinguish different signature parts, some are habitual, while others are different each time they sign.

The use of signatures has been widely accepted, with applications ranging from declarations of independence to credit cards. However, the problem of signature recognition still exists in the way of obtaining the metrics used in the recognition process and the repeatability of the signature. The DSV system has been controlled to accept variables in some way. However, without reducing the acceptance rate, it cannot continuously measure the strength of the signature.