The research on facial recognition systems began in the 1960s. After the 1980s, with the development of computer technology and optical imaging technology, the true application stage of the early 1990s was in the late 1990s; In recent years, artificial intelligence technology has been continuously advancing, and facial recognition technology has developed rapidly. The "Face Recognition System" integrates various professional technologies such as artificial intelligence, machine recognition, machine learning, model theory, expert systems, and video image processing. It is a highly comprehensive system engineering technology

Face recognition process:

Face recognition systems typically include several processes: facial image acquisition and detection, key point extraction, facial regularization (image processing), facial feature extraction, and facial recognition comparison.

Facial image set. Different facial images can be captured through the camera lens, such as static images, dynamic images, different positions, and different expressions. It can be well collected. When the user collects the shooting range of the device, the collection device will automatically search for and capture the user's facial image Face detection. Face detection is mainly used for preprocessing of face recognition, which accurately calibrates the position and size of the face in the image Key point extraction (feature extraction). The features available for facial recognition systems are usually divided into visual features, pixel statistical features, facial image transformation coefficient features, and facial image algebraic features. Facial feature extraction is based on certain features of the face. Facial feature extraction, also known as facial markers, is the process of modeling facial features. The methods for extracting facial features can be classified into two categories: one is knowledge based representation methods; Another method is based on algebraic features or statistical learning Faces are regular (pre processed). Facial image preprocessing is based on the results of facial detection, processing the image, and ultimately serving the feature extraction process. Due to various conditions and random interference, the original images obtained by the system often cannot be directly used. They must be directly used in the early stages of image processing. For facial images, the preprocessing process mainly includes light compensation, grayscale transformation, histogram equalization, component and geometric correction, filtering, and sharpening to process grayscale Face recognition comparison (matching and recognition). Search for extracted facial image feature data and match it with feature templates stored in the database. By setting a threshold, when the similarity exceeds this threshold, the matching result is output. Face recognition is the process of comparing the facial features of others to be recognized with the already obtained facial feature templates, and determining the identity information of the face based on the degree of similarity. It can be divided into 1:1, 1: n, and attribute recognition. Among them, 1: 1 is to compare the eigenvalues of two faces, and 1: N is to compare the eigenvalues of one face photo with the eigenvalues of another face. The faces with the highest degree of similarity or similarity are ranked first. Face feature analysis algorithms

Face recognition technology is widely used in regional feature analysis algorithms. It integrates computer image processing technology and biostatistics principles. Using computer image processing technology to extract portrait feature points from videos, and using biostatistics principles to analyze and establish mathematical models, namely facial feature templates. Perform feature analysis using the completed facial features of the person and the facial feature template of the subject, and provide similarity values based on the analysis results. By using this value, it can be determined whether it is the same person There are many recognition methods for facial recognition. The main facial recognition methods include:

(1) Geometric feature facial recognition methods: Geometric features can be the shapes of eyes, nose, mouth, etc. And the geometric relationship between them (such as the distance between them). These algorithms have fast recognition speed, small memory, but low recognition rate (2) Face recognition method based on feature face (PCA): The feature face method is a face recognition method based on KL transform. The KL transform is the best orthogonal transform for image compression. After KL transformation, a new set of orthogonal groups is obtained, retaining important orthogonal groups. These bases can be opened up to low dimensional linear space. If the projections of the face in these low dimensional linear spaces are segmented, these projections can be used as feature vectors for identity recognition. This is the basic idea of the feature face method. These methods require more training samples and are entirely based on image grayscale statistics. There are currently some improved features available