Face Recognition Technology Knowledage
Author: huifan Time: 2020-09-28
The police recognize your face through face recognition security camera CCTV surveillance cameras on the street, and will tell you whether you are sad or happy now. Your ID can be checked on the system if you have a criminal record? How likely is your face to overlap with someone else's face? Do you have a way to avoid facial surveillance?
What is face recognition?
Face recognition database is a kind of biometric recognition technology based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing faces, and automatically detect and track faces in the images, and then perform facial recognition on the detected faces, usually also called face recognition and facial recognition .
How does face recognition work?
Face recognition deep learning
The face recognition system mainly includes four components: face image acquisition and detection, face image preprocessing, face image feature extraction, and matching and recognition.
Face image collection and detection
Face image collection: Different face images can be collected through the camera lens, such as static images, dynamic images, different positions, different expressions, etc. can be well collected. When the user is within the shooting range of the capture device, the capture device will automatically search for and shoot the user's face image.
Face detection: In practice, face detection is mainly used for preprocessing of face recognition, that is, to accurately calibrate the position and size of the face in the image. The pattern features contained in face images are very rich, such as histogram features, color features, template features, structural features, and Haar features. Face detection is to pick out the useful information, and use these features to realize face detection.
The mainstream face detection method uses the Adaboost learning algorithm based on the above features. The Adaboost algorithm is a method for classification. It combines some weaker classification methods together to form a new strong classification method.
In the face detection process, the Adaboost algorithm is used to select some rectangular features (weak classifiers) that best represent the face, and the weak classifier is constructed into a strong classifier according to the weighted voting method, and then several strong classifiers obtained by training A cascade structure of stacked classifiers is formed in series, which effectively improves the detection speed of the classifier.
Face image preprocessing
Face image preprocessing: The image preprocessing of the face is based on the face detection result, the image is processed and finally serves the process of feature extraction. Due to various conditions and random interference, the original image acquired by the system cannot be used directly. It must be preprocessed by grayscale correction and noise filtering in the early stage of image processing. For face images, the preprocessing process mainly includes light compensation, gray scale transformation, histogram equalization, normalization, geometric correction, filtering and sharpening of the face image.
Face image feature extraction
Face image feature extraction: The features that can be used in a face recognition system are usually divided into visual features, pixel statistical features, face image transformation coefficient features, and face image algebraic features. Facial feature extraction is based on certain features of the human face. Face feature extraction, also known as face representation, is a process of feature modeling of human faces. Facial feature extraction methods can be summarized into two categories: one is knowledge-based representation methods; the other is based on algebraic features or statistical learning.
The knowledge-based representation method is mainly based on the shape description of the face organs and the distance characteristics between them to obtain feature data that is helpful for face classification. Its feature components usually include the Euclidean distance, curvature, and angle between feature points. . The human face is composed of parts such as eyes, nose, mouth, and chin. The geometric description of these parts and the structural relationship between them can be used as important features to recognize the face. These features are called geometric features. Knowledge-based face representation mainly includes geometric feature-based methods and template matching methods.
Face image matching and recognition
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. Face recognition is to compare the facial features to be recognized with the obtained facial feature template, and judge the identity information of the face based on the degree of similarity. This process is divided into two categories: one is confirmation, which is a process of one-to-one image comparison, and the other is identification, which is a process of one-to-many image matching and comparison.
Generally speaking, a face recognition software system includes image capture, face positioning, image preprocessing, and face recognition (identity confirmation or identity search). The input of the system is generally one or a series of face images with undetermined identities, and several face images with known identities in the face database or corresponding codes, and the output is a series of similarity scores, indicating The identity of the face to be recognized.
Feature-based recognition algorithms based on facial feature points.
Appearance-based recognition algorithms based on the entire face image.
Template-based recognition algorithms.
Recognition algorithms using neural network.
Neural network recognition
Based on light estimation model theory
A lighting preprocessing method based on Gamma gray correction is proposed, and corresponding lighting compensation and lighting balance strategies are carried out based on the lighting estimation model.
Optimized deformation statistical correction theory
Based on the correction theory of statistical deformation, optimize the face pose; strengthen the iterative theory
The enhanced iteration theory is an effective extension of the DLFA face detection algorithm;
Original real-time feature recognition theory
This theory focuses on the intermediate value processing of real-time face data, so as to achieve the best matching effect between the recognition rate and the recognition performance
Face recognition application
The application of face recognition in the business field is mainly business intelligence analysis system. In physical commerce, the attracting of target customers and precision marketing have become important expenditures of commercial costs. The efficiency of traditional passive shopping mall identification, manual push and shopping guide methods has declined, making precision marketing centered on artificial intelligence a new business growth point. The face recognition system can make full use of the feature recognition and induction capabilities of machine vision to recognize the customer’s gender, age, mood, etc. as the corresponding features of business needs, and push targeted real-time content that customers are interested in to target businesses. Customer group diversion and precision marketing; on the other hand, by observing and learning the interests of different groups of people, gradually improve the accuracy of matching the content pushed by the target group.
Smart Public Security:
The application of face recognition in the field of public security focuses on the realization of registration and management of illegal personnel, online pursuit of escape, verification and verification and post-event processing. At the same time, portrait comparison can also be used in criminal investigations and maintaining social stability. The face recognition photo comparison system is used for fast identification, searching for the identity of a specific person in a large number of databases. It makes full use of very valuable face photo clues to greatly speed up the identification process of suspects by public security investigators. In order to speed up the process of "strengthening the police with science and technology", it forms a highly intelligent, socialized and large-scale public security prevention system. Provides effective technical means.
Smart security check:
With the current acceleration of urban life and the continuous improvement of living standards, aircraft and railway safety have received more and more attention. Nowadays, many airports have begun to use high-definition face ID comparison systems to assist the airport's manual inspection work. When a passenger is about to enter the waiting hall, the camera at the security checkpoint will automatically capture the face image, and the face recognition system will automatically compare the passenger's ID photo with it to identify the passenger. When the certificate information is found to be inconsistent with the certificate holder, the system will automatically prompt the security check personnel to strengthen manual verification. The face images collected by the face recognition system can also be recorded as very important monitoring data, stored in the database, used as an index for subsequent retrieval, or connected to the database of the public security and security departments for evidence collection and identification.
An industrial revolution driven by a new generation of technology represented by face recognition has emerged. This new economic unit will be an era of technological competition, and technical barriers will become higher and higher.
You are welcome to explore various technologies of face recognition with us.
Youtube: Huifan Technology
Linkedin: Huifan Technology
Facebook: Huifan Technology
Whatsapp: +86 15523810826