Disadvantages of face recognition technology

From a technical point of view, the human face is the only biometric information that can be collected without the user's active cooperation. The collection process of other biometrics, such as fingerprints, palm prints, irises, veins, and retinas, must be based on the user's active cooperation, that is, if the user refuses to collect, high-quality feature information cannot be obtained. From the perspective of psychology, it is easy to be accepted by users through face recognition identity and human visual recognition experience. For example, when people collect fingerprints and irises, they will worry about privacy leaks, but they are photographed by hundreds of surveillance cameras on the street every day, but they don't feel invaded because the faces are naturally exposed and are considered to be natural features of identity recognition. So let's talk about the drawbacks of face recognition technology.

Face recognition technology belongs to biometric recognition technology, which is a biological feature of an organism (generally referred to as a person) to distinguish organisms. Face recognition technology refers to the use of computer technology for analysis and comparison to identify faces.

"The existing face recognition system can achieve satisfactory results when the user cooperates and the acquisition conditions are ideal. However, the recognition rate of the existing system will be abrupt when the user does not cooperate and the acquisition conditions are not ideal. Declining. Face recognition technology is far from practical, and there are still many challenging problems to be solved.” In an interview with Beijing Youth Daily, Tan Xiaoyang introduced this.

For example, when the face is compared, there is a discrepancy between the face stored in the system, such as shaving a beard, changing a hairstyle, having more glasses, and changing the expression may cause the comparison to fail. In other words, if a person makes a small change, the system may fail the authentication. Today, conservative estimates, face recognition technology can reach 95% accuracy, but not 100%. At the same time, for twins, face recognition is almost impossible to complete due to too many similar features.

Zhang Xiaobo, Ph.D., of the Institute of Automation, Chinese Academy of Sciences, also believes that lighting, posture, decoration, etc. have an impact on the machine recognition of the human face. Currently in the United States there are some of the world's most advanced face recognition systems, which identify 1% of misreading rates when testing.

Su Guangda said that nowadays, for face image acquisition in non-cooperating situations, the occlusion problem is very serious. Especially in the monitoring environment, the monitored object may wear glasses, hats and other accessories, so that the captured face image may be incomplete, which affects the subsequent feature extraction and recognition, and even leads to the face detection algorithm. Invalid. How to effectively remove the influence of obstructions is a very urgent research topic.

At the same time, the appearance of the face changes with age, especially for adolescents. The recognition rate of face recognition algorithms is different for different age groups. The impact of age changes on face recognition algorithms must also be addressed.

In addition, although the size of the face recognition algorithm will decrease with the increase of the size of the face database, how to maintain or improve the recognition rate of the face recognition algorithm in large-scale application environment is also a very important issue.

According to foreign media reports, the top social networking company Facebook has quietly launched the face recognition technology that automatically recognizes photo characters last year, triggering a new round of privacy leaks.

Facebook's "tag recommendation" feature uses facial recognition technology to make it easier for users to tag their friends and relatives. Facebook automatically turns this feature on for users, which is enabled in the US and most countries. Facebook responded when faced with outside questions. "When we launched this service, we should have made the user more clear." Facebook also said through a statement that the photo tag recommendation function is only activated when uploading a new photo to Facebook, only friends are Recommended, and users can turn it off with privacy settings.

Photo software and online services such as Google PICasa and Apple iPhoto also use face recognition technology, but Facebook has more than 500 million users, and the use of face recognition technology is bound to lead to more difficult privacy issues.

Glass Display

Glass Display,High Transparency Led Glass Digital Screen,Glass Window Led Advertising Display,High Level Outdoor Glass Led Display

Kindwin Technology (H.K.) Limited , https://www.szktlled.com