Facial recognition gate is the application development trend of facial recognition system software in gate, face recognition and artificial service method service item identification, other extensive microbial discrimination technical gate, IC and ID credit card and valid document gate, etc. Checking has outstanding advantages and innovation. Compared with the service item identification of the manual service method, the face recognition gate replaces the traditional manual service method service item method to implement real-name authentication, which is more efficient and more detailed. Checking with other types of microbiological identification technology gates, such as fingerprint recognition, fundus macular, and hand, face recognition gates have many advantages.Face recognition gateDifferent from the gates used alone, in addition to swiping cards and QR codes to open gates, you can also use face recognition (face swiping) to open gates, which not only enhances the experience of entering and exiting, but also enhances security.

1. Facial recognition gate image collection and detection

Different face images can be collected through the camera lens, such as static images, dynamic images, different positions, different expressions, etc. can be collected very well. When the user is within the shooting range of the collection device, the collection device will automatically search for and capture the user's face image. The accuracy rate of the face recognition gate is 99.4% (under the 10,000th false recognition rate), and the accuracy rate is 99.5%

Face detection is mainly used in the preprocessing of face recognition in practice, that is, the position and size of the face are accurately marked in the image. The facial features contained in the face image are very rich, such as histogram features, color features, template features, structural features, and so on. Face detection is to pick out the useful information and use these features to realize face detection.

2. Face image matching and recognition

The feature data of the extracted face image is searched and matched with the feature template stored in the database. By setting a threshold, when the similarity exceeds this threshold, the matching result is output. The face recognition system compares the face features to be recognized with the face feature templates that have been entered, and judges the identity information of the face according to the degree of similarity. This process is divided into two categories: one is confirmation, which is a one-to-one image comparison process, and the other is recognition, which is a one-to-many image matching and comparison process. Face recognition accuracy rate exceeds human eye accuracy and strong compatibility: Wiegand output + relay output, widely applicable to different types of access control gate channels

3. Face image preprocessing in the face recognition gate access control system

The image preprocessing for human faces is based on the face detection results, processing the image and serving the process of feature extraction. The original image acquired by the system is often unable to be used directly due to various conditions and random interference. It is preprocessed in the early stages of image processing such as grayscale correction and noise filtering. For face images, the preprocessing process mainly includes light compensation, grayscale transformation, histogram equalization, normalization, geometric correction, filtering and sharpening of the face image.

4. Face image feature extraction of face recognition gate

Face image feature extraction: The features that can be used in face recognition systems are generally divided into visual features, pixel statistical features, facial image transformation coefficient features, and facial image algebraic features. Face feature extraction is carried out for certain features of face. Face feature extraction, also known as face characterization, is a process of feature modeling for human faces. The methods of facial feature extraction can be divided into two categories: one is based on knowledge representation method; the other is based on algebraic features or statistical learning representation method.