Biometric technology, through the close combination of computer and high-tech means such as optics, acoustics, biosensors and biostatistics, uses the inherent physiological characteristics of human body (such as fingerprint, face image, iris, etc.) and behavioral characteristics (such as handwriting, sound, gait, etc.) to identify personal identity.
Biometric technology is the most convenient and safe identification technology at present. According to the prediction of U.S. consulting agency transparency market research, the global biometric technology market scale will increase from US $11.24 billion in 2015 to US $23.3 billion in 2020, with a compound annual growth rate of 15.7%. The biometric market is growing rapidly.
In the global biometric market structure, fingerprint recognition accounts for 58%, and face recognition accounts for 18%, followed by the emerging iris recognition, with a share of 7%. In addition, there are palmprint recognition similar to fingerprint recognition, voiceprint recognition and vein recognition. What are the advantages and disadvantages of each biometric recognition, what difficulties need to be overcome in the process of industrialization, and what are the representative enterprises of each type of biometric? Today’s article will tell you in detail.
Face is born like other biometrics (fingerprint, iris, etc.) of human body. Its uniqueness and good characteristics that are not easy to be copied provide a necessary premise for identity identification. Compared with other types of biometrics, face recognition has the following characteristics:
Non mandatory: users do not need to cooperate with face acquisition equipment, and can obtain face images almost unconsciously. Such sampling method is not “mandatory”;
Non contact: users can obtain face images without direct contact with the device;
Concurrency: multiple faces can be sorted, judged and recognized in practical application scenarios;
In line with the visual characteristics: “recognize people by appearance”, as well as the characteristics of simple operation, intuitive results and good concealment.
At present, face recognition technology is very mature, and the domestic industrial chain tends to be improved. At present, almost all computer vision enterprises are doing face recognition, such as face + +, Geling deep pupil, Shangtang technology, Zhongke Shituo, etc.
While face recognition has high convenience, its security is also relatively weak. The recognition accuracy will be affected by many factors, such as ambient light, recognition distance and so on; In addition, when users make some changes to the face through makeup and cosmetic surgery, it will also affect the accuracy of face recognition. These are the technical problems that enterprises urgently need to break through.
China’s second-generation ID card has realized fingerprint collection, and major smart phones have realized fingerprint unlocking function. Compared with other biometric technologies, fingerprint identification has been widely used in consumer electronics, security and other industries. Through the test of time and practice, the technology is also constantly innovating. At present, China has already formed a complete fingerprint identification industry chain. For example, huiding technology, a listed enterprise engaged in fingerprint chip design, and a number of domestic fingerprint identification chip manufacturers such as siliwei, feinger and Mindray.
Although everyone’s fingerprint identification is unique, it is not applicable to every industry and everyone. For example, people who work by hand for a long time will be worried about fingerprint recognition. If their fingers are damaged or stained with foreign matters in dry and wet environment, the fingerprint recognition function will fail. In addition, it will also make fingerprint identification less convenient in cold areas or cold climates, or in environments where people need to wear gloves for a long time.
Human eye structure consists of sclera, iris, pupil, lens, retina and so on. After the formation of iris in fetal development, it will remain unchanged throughout life. These features determine the uniqueness of iris features and identity recognition. Therefore, the iris feature of the eye can be regarded as the identification object of each person.
According to Fujitsu’s data, the false identification of iris recognition may be 1 / 1500000, while the false identification of apple touchid may be 1 / 50000. The accuracy of iris recognition is up to 30 times that of the current fingerprint scheme, and iris recognition belongs to non-contact recognition, which is very convenient and efficient. In addition, iris recognition also has the characteristics of uniqueness, stability, non replicability and in vivo detection. It occupies an absolute advantage in comprehensive security performance, and the security level is the highest at present.
At present, iris recognition has been widely used in the fields of finance, medical treatment, security inspection, security, special industry attendance and access control, industrial control and so on. Domestic representative manufacturers in the field of iris recognition include Zhongke Hongba, Hongxing technology, Juhong optoelectronics, Wuhan Hongzhi, code interpretation Dahua, etc.