From Google, Facebook to BAT, from social security to campus access, face recognition will become a convenient "master key." But the debate about the accuracy, security, and privacy of face recognition in the industry has never stopped.
Face recognition market application outbreak
Face recognition, also known as face recognition and face recognition, is a method of capturing an image or video stream containing a face by using a camera or a camera, and automatically detecting and tracking the face in the image, thereby performing face detection on the detected face. A series of related technologies. The research of face recognition system began in the 1960s. After the 1980s, with the development of computer technology and optical imaging technology, the application stage that really entered the primary stage was in the late 90s, with the technology of the United States, Germany and Japan. Realized as the main.
Domestic face recognition market Since March 2015, Ma Yun bought a set of commemorative stamps with Alipay “brush face†at the Hanover Electronics Show in Germany, which became the first prototype of the domestic face recognition technology applied to the commercial field. The face recognition application market has also exploded. Subsequently, major Internet giants have also launched brush-related applications.
In fact, face recognition technology originated earlier in the security industry. Through face recognition technology, the rapid identification of social unrest in crowded people is the basic requirement of public social security; through the joint detection of scenic faces, intelligent control of scenic spot flow; and attendance, smart lock, ID card Application in areas such as information verification.
Today, face recognition technology has become a society-wide, all-field application technology.
In the field of Internet finance, Ping An Pratt & Whitney launched the “Peace I Loan†in July 2015. In mid-August of the same year, Weizhong Bank launched the APP with “Face Recognition†function; Collaborate to apply face recognition technology to the online loan certification process. In Tencent's WeChat wallet, we launched a micro-securities product, recommending users to “paint their faces†to open an account; Jingdong wallet is not to be outdone, and has also achieved “brushing face†to unlock.
In the field of human society, Neusoft Group is the most representative social security service software provider in China. Its products cover nearly 200 cities and benefit 400 million people. It is one of the main forces to help people organizations build online platforms. In order to enhance the basic ability and risk control ability of the human society - that is, to accurately identify the authenticity of the user's identity and integrate user data, and to provide a convenient and safe certification environment for the public, Neusoft Group cooperated with the "Face" to launch the "agement" The Applicant Appraisal App and the “People's Insured Registration App†help the social management agencies and citizens to implement remote authentication and social security registration through face recognition technology.
According to relevant forecasts, from 2015 to 2020, the face recognition market will grow at a rate of 166.6%, while the domestic face recognition market will reach 100 billion yuan. Throughout the domestic market, the average compound growth rate of China's face recognition market is 15.9%. In the same period, China's market size accounted for about 10% of the global face recognition market. Compared with the proportion of China's population and city size, although the value of the face recognition market is slightly lower, with the continuous development of face recognition technology in China, China's face recognition market will usher in an outbreak.
At the 2016 National Cyber ​​Security Publicity Week, the important role of biometrics in Internet security and information authentication has attracted a lot of attention. The consensus of the industry is: With the improvement of the algorithm, biometrics technology has achieved a major breakthrough, and in more and more fields, it has continuously crossed the threshold of user acceptance, and its market has exploded rapidly. Among them, the domestic market size of face recognition is expected to reach 100 billion in the next five years.
Although face recognition is hot, the technical limitations still need to be broken.
With the penetration of face recognition into the basic financial field, this biometric technology, which has existed for more than 10 years, has suddenly opened up a huge imagination. However, as with every science and technology that is so successful, its potential potential threats are also scary. In the United States, the hidden dangers brought by the face recognition technology have caused many technology giants such as Facebook and Google to get into the fire.
At present, the algorithm of face recognition is less than 100% accurate. "In this world, there are people who look a lot like you. When you search for you from 10 million face pictures, it is very likely that you are not the one who looks like you." The recognition does not reach the high accuracy of biometrics such as fingerprints or irises.
Moreover, unlike fingerprints and irises, face morphology is not constant for life, but may change with time. This is also a difficult point that cannot be avoided in face recognition technology. It is understood that the current face recognition technology can be done, the face can be identified in the case of hair changes, regular makeup, a certain degree of fat and thin changes, natural aging and so on. However, if the face appears too drastically changed due to cosmetic surgery, etc., the computer's face recognition technology can't do anything. In addition, face recognition for twins and multiple births is also very difficult. At present, only a combination of multiple recognition methods can be used for identification.
In addition, face recognition is also very sensitive to the scene lighting environment. The current face recognition technology mainly recognizes the relative position of the face and the facial features by plane 2D, and it has the possibility of deceiving the machine in the form of a photo. “But in the absence of coordination, identification bias may occur, such as when your cousin is more like you than you.â€
But overall, the accuracy of face recognition has exceeded the human eye. Especially after 2013, with the maturity of hardware and software technology, the industry has entered a real outbreak period.
Conclusion: Every technology has its advantages and disadvantages. A perfect balance between security and convenience is the technology most needed in the market. Therefore, from this perspective, the integration of various information technologies in the future is an inevitable trend. "Wangshan runs dead horse", we seem to have seen the "ultimate safety" mountain, but we have a long way to get closer to it.
The optical dome is mainly used to protect precision instruments, and the camera is used in harsh environments. Common optical glass domes are made of H-K9L produced by Chengdu Guangming, N-K5, N-BK7, and N-BK10 produced by German Schott Company, and S-BSL7 produced by Japanese Kohara Company.
These materials have a common feature: the cost of the blank is relatively low, the optical performance is excellent, the mechanical properties of the material are better than other high-refractive materials, and the acid resistance, alkali resistance, and moisture resistance are excellent. It can be used for a long time in a complex environment and has a better protection effect. These materials have good transmittance in the spectral range of 280nm~2650nm. It can be widely used in underwater camera protection, high-definition outdoor monitoring equipment lens protection, radiation measuring instrument protection.
A meniscus lens composed of two spherical surfaces with small radius of curvature and little difference in value.
The meniscus lens is a meniscus lens. This lens has a convex mirror surface and a concave mirror surface. If the outward arc is greater than the inward arc, the lens has a positive focal length and serves as a magnifying glass. United Optical Technology provides uncoated meniscus lenses and IR2 antireflection coated meniscus lenses. Germanium (Ge) substrates are suitable for infrared applications.
Optical Glass Dome,Optical Dome Lens,Hemispherical Dome,N-Bk7 Dome Lens
Bohr Optics Co.,Ltd , https://www.bohr-optics.com