The biometrics market is experiencing rapid growth and will see new changes and demands
Author: huifan Time: 2019-11-18
In the global biometric market structure, the fingerprint recognition share is 58%, and the face recognition share is 18%, followed by the emerging iris recognition with a share of 7%. In addition, there is palmprint recognition similar to fingerprint recognition. , as well as voiceprint recognition and vein recognition. What are the advantages and disadvantages of each biometric identification? What difficulties need to be overcome in the process of industrialization? And what are the representative companies for each type of biometrics?
The human face is as natural as other biological characteristics of the human body (fingerprint, iris, etc.). Its uniqueness and good characteristics that are not easily reproduced provide the necessary premise for identity identification, and face recognition compared with other types of biometrics. Has the following characteristics:
Non-mandatory: the user does not need to cooperate with the face collection device, and the face image can be obtained almost in an unconscious state. Such sampling method is not “mandatory”;
Non-contact: Users can obtain facial images without direct contact with the device;
Concurrency: In the actual application scenario, multiple face sorting, judgment and recognition can be performed;
It conforms to the visual characteristics: the characteristics of “seeing people”, as well as the features of simple operation, intuitive results and good concealment.
At present, the face recognition technology is very mature, and the domestic industrial chain is also becoming more and more perfect. At present, almost all computer vision enterprises are doing face recognition, such as Vision Technology, Geling Squat, Shangtang Technology, and Christie Extension and so on.
Face recognition has a relatively high level of convenience while its security is relatively weak. The accuracy of recognition will be affected by many factors such as the ambient light and recognition distance. In addition, when the user makes some changes to the face through makeup and facelifting, it will also affect the accuracy of face recognition. These are all technical problems that enterprises need to break through.
China's second-generation ID card has achieved fingerprint collection, and all major smartphones have realized fingerprint unlocking. Compared with other biometric technologies, fingerprint recognition has been widely used in consumer electronics, security and other industries. Through time and practice testing, technology is constantly innovating. At present, China has already formed a complete fingerprint identification industry chain. For example, Huiding Technology, a listed company engaged in fingerprint chip design, and a domestic fingerprint identification chip manufacturer such as Si Liwei, Fei Engel and Mindwei.
Although each person's fingerprint recognition is unique, it does not apply to every industry and everyone. For example, people who work with their hands for a long time will be troubled by fingerprint recognition. If their fingers are damaged or wet or dry, the fingerprint recognition function will be invalid. In addition, in an environment with severe cold or cold weather, or where people need to wear gloves for a long time, this will make fingerprint recognition less convenient.
The structure of the human eye consists of the sclera, iris, pupillary lens, retina and the like. After the iris is formed in the fetal development stage, it will remain unchanged throughout the life course. These characteristics determine the uniqueness of the iris characteristics and also determine the uniqueness of the identity. Therefore, the iris feature of the eye can be used as an identification object for each person.
According to Fujitsu data, the iris recognition error recognition may be 1/1500000, while the Apple TouchID error recognition may be 1/50000, the iris recognition accuracy is up to 30 times that of the current fingerprint scheme, and the iris recognition is non-contact. Recognition, recognition is very convenient and efficient. In addition, iris recognition is unique, stable, non-replicable, and in vivo detection. It has an absolute advantage in comprehensive safety performance, and the safety level is currently the highest.
At present, iris recognition has been widely used in financial, medical, security, security, special industry attendance and access control, industrial control and other fields due to its high accuracy and ease of use. Domestic representatives in the field of iris recognition include Zhongke Hongba, Hongxing Technology, Juhong Optoelectronics, Wuhan Rainbow, and Dahua.
The palm vein recognition system first obtains the palm vein distribution map through the vein recognition instrument, extracts the feature value from the palm vein distribution map according to the special comparison algorithm, and obtains the image of the finger, the palm, the back vein of the hand through the infrared CCD camera, and the digital image of the vein. Stored in a computer system to store feature values.
Vein recognition has four characteristics: high anti-counterfeiting, easy to use, fast identification and high accuracy. The most important point is that the characteristics of the finger vein recognition have been internationally recognized as unique and comparable to the retina, in the case where the rejection rate (the same structure map, but the algorithm is identified as different) is less than one in ten thousand. The false recognition rate (different structure diagram, which is recognized by the algorithm as the same) can be less than one in 100,000. But it also has the disadvantages that are difficult to circumvent:
(1) The dorsal vein of the hand may still change with age and physiology, and the permanent has not been confirmed;
(2) There is still the possibility that registration cannot be successful;
(3) Because the collection method is limited by its own characteristics, it is difficult to miniaturize the product;
(4) The collection equipment has special requirements, the design is relatively complicated, and the manufacturing cost is high.
At present, the application of vein recognition function in the market is not high. The well-known domestic enterprises are Fujitsu, Tongyuan Micro-Intelligence Technology, and Zhimai Technology.
The advantages of voiceprint recognition compared to other biometrics are:
(1) The sound pattern extraction is convenient and can be completed without knowing it, so the user's acceptance is also high;
(2) The recognition of the acquired voice is low in cost, simple to use, and a microphone can be used, and no additional recording equipment is needed when using the communication device;
(3) Suitable for remote identity verification, only need a microphone or phone, mobile phone can be remotely logged through the network (communication network or internet);
(4) The algorithm for voiceprint recognition and confirmation is low in complexity;
(5) With some other measures, such as content recognition through speech recognition, the accuracy can be improved. These advantages make the application of voiceprint recognition more and more popular among system developers and users.
Of course, the application of voiceprint recognition has some drawbacks:
(1) The voice of the same person is temperable and susceptible to physical conditions, age, mood, etc.;
(2) Different microphones and channels have an impact on the recognition performance;
(3) Ambient noise has interference with identification;
(4) In the case of a mixed speaker, the voiceprint characteristics of the person are not easily extracted.
Therefore, voiceprint recognition is still mainly used in some scenes where the identity security requirements are not too high, such as the now popular smart audio. At present, the domestic Science and Technology News, Spirent, SpeakIn, and Yunzhisheng have launched corresponding voiceprint recognition technology.
Gait recognition is a non-contact biometric technology. Because it does not require human behavior; it is especially suitable for long-distance identification. This is unmatched by any biometric identification; it is not easy to disguise. It is a means of chasing criminals. It can not only analyze the actions of suspects caught by closed-circuit television, but also compare them with the attitude of suspects walking. In some homicides, the murderers often prevent you from seeing their faces, but they can see the way the murderer walks. The collection device is simple and economical. Because only one surveillance camera is needed.
At present, the enterprises in the field of domestic gait recognition are most famous for the Milky Way.
To sum up
Biometrics will also usher in new changes and demands. The intersection of biometrics and the Internet and the Internet of Things will become the focus of various industries. The current single biometric technology has its own advantages and disadvantages, and some problems will inevitably arise in the application. Therefore, in some application scenarios with high security level requirements, two or more biometric technologies are often used for verification. With the advent of the Internet of Things era, biometrics will have a broader market prospect.