With the widespread use of software and hardware technologies related to digital images in people's lives, digital images have become an important component of information sources in contemporary society, and the needs and applications of various image processing and analysis have also continuously prompted the innovation of this technology. Today, let’s talk about a biometric technology that is considered dangerous based on human facial feature information—face recognition technology.
1. Overview of face recognition
The research on the face recognition system began in the 1960s. After the 1980s, it was improved with the development of computer technology and optical imaging technology, but it really entered the primary application stage in the late 1990s, and the United States, Germany and Japan The key to the success of the face recognition system is whether it has a cutting-edge core algorithm, and makes the recognition result have a practical recognition rate and recognition speed; the "face recognition system" integrates artificial intelligence, machine recognition, machine Learning, model theory, expert system, video image processing and other professional technologies, combined with the theory and implementation of intermediate value processing, is the latest application of biometric identification. The realization of its core technology shows the transformation from weak artificial intelligence to strong artificial intelligence. Intelligent transformation.
2. The double-sided nature of face recognition technology
Facial recognition technology is not guilty, and steel is sometimes used to make baby incubators and sometimes guns. "Amazon CTO Werner Vogels said about the "dilemma" encountered by the implementation of face recognition technology. He believes that all technologies are double-sided and can have good applications or be used maliciously. Determine the development of technology The direction of development depends on the choice of the regulatory authorities. Of course, the process of all technologies from 0 to 1 and from 1 to N is a process of constantly complementing their own shortcomings. In this regard, many companies have also begun to tackle difficulties. Facebook has released Fairness Flow, a tool that automatically warns whether an algorithm has made unfair judgments based on the race, gender, or age of the detection target. Now, by working with artificial intelligence fairness experts, Microsoft has revised and Expanded its Face API dataset for model training. Face API is a Microsoft Azure API that mainly provides algorithms for detecting, recognizing and analyzing face content in images. Through a large number of new datasets related to skin color, gender and age According to data, Face API can now reduce the misjudgment rate of dark-skinned men and women to one-twentieth of the original, and the misjudgment rate of women to one-ninth of the original. Meanwhile, the start-up Gfycat company Also this year, it said it would introduce stricter detection thresholds in an effort to improve the accuracy of its facial recognition algorithms in identifying faces of people of Asian descent.
3. In-depth learning of face recognition
To learn face recognition technology, I have the most comprehensive "Artificial Intelligence Self-study Video", which has a full 60G, and I will share it with you!
It has been sorted out for a long time and is very comprehensive. Including some artificial intelligence basic introductory videos + AI common framework combat videos, image recognition, OpenCV, NLQ, YOLO, machine learning, pytorch, computer vision, deep learning and neural network and other videos, courseware source code, well-known domestic and foreign elite resources, AI popular Papers, industry reports and more.
Friends in need can private message me, hoping to help those in need.