Face recognition is a biometric technology based on human face feature information. It uses a camera or a camera to capture an image or video stream containing a human face, and automatically detects and tracks the face in the image, and performs related processing on the detected face. Face recognition needs to accumulate a large amount of data related to face images to validate the algorithm and continuously improve the recognition accuracy.
Existing face recognition systems can achieve satisfactory recognition results under ideal conditions of user collaboration and acquisition. However, the recognition rate of existing systems will suddenly decrease under the condition of non-cooperation of users and less than ideal conditions of acquisition. For example, when comparing a face with a face stored in the system, such as shaving, changing hairstyle, wearing more glasses, or changing expressions may cause the comparison to fail.
Face recognition technology is one of the widely used regional feature analysis algorithms in biometric technology, which integrates computer image processing technology and biostatistics principles in one, using computer image processing technology to extract human image feature points from video and using biostatistics principles to analyze and establish mathematical models, i.e. face feature templates. The completed face feature template is used to analyze the features with the face image of the subject, and a similarity value is given according to the result of the analysis. This value is used to determine if the person is the same.
The advantage of face recognition lies in its naturalness and the absence of perceived features of the tested individual. By naturalness, we mean that the recognition method is the same as the biometric features used by humans in individual identification. For example, face recognition distinguishes individuals by observing and comparing faces and distinguishing identities, plus natural recognition as well as voice recognition, body type recognition, etc. Fingerprint recognition, iris recognition, etc. are unnatural because humans or other organisms do not distinguish individuals by such biometric features. Undetected features are also important in recognition methods, which makes them inoffensive and less likely to be deceptive, as it is less likely to attract attention. Face recognition has such characteristics that it uses visible light exclusively to acquire information about face images, but unlike fingerprint recognition or iris recognition, which require the use of electronic pressure sensors to capture fingerprints, or infrared light to capture iris images, these particular capture methods are easily detected and therefore more easily spoofed by disguises.
Face recognition is considered to be one of the difficult research topics in the field of biometric recognition and even artificial intelligence. The difficulty of face recognition is mainly caused by the characteristics of the face as a biometric feature, where the differences between different individuals are very small and the structure of the face is similar, even the structure and shape of the face organs are very similar, and this feature is beneficial to the use of face localization but not to face recognition. The shape of the human face is very unstable, and people can produce many expressions by the changes of the face, and the visual image of the face changes a lot on different observation angles. In addition, face recognition is affected by many factors, such as lighting conditions, mask of the face, age, etc.
In face recognition, one type of variation should be magnified to serve as a criterion to distinguish individuals, while another type of variation should be eliminated because they can represent the same individual. One type of variation is usually referred to as interclass variation and the other as intraclass variation. For faces, intra-class variation tends to be greater than inter-class variation, which makes it difficult to distinguish individuals by inter-class variation with the interference of intra-class variation. Face recognition is mainly used for identity recognition. Due to the rapid popularity of video surveillance, many video surveillance applications urgently need a long-distance, non-cooperative state fast identification technology to quickly confirm the identity of remote personnel and achieve intelligent warning. Face recognition technology is undoubtedly a good choice. Using fast face detection technology can find faces from surveillance video images in real time and compare with face database in real time, thus realizing fast identification.
face recognition device
As an emerging biometric identification technology (Biometrics), face recognition technology has unique advantages in application compared with iris recognition, fingerprint scanning, palm scanning and other technologies: easy to use, high user acceptance Face recognition technology uses a universal camera as a recognition information acquisition device to complete the recognition process in a non-contact manner without the recognition object noticing Recognition process. Intuitive outstanding face recognition technology is based on the human face image, and the human face is undoubtedly the most intuitive source of information that can be discriminated by the naked eye, which is convenient for manual confirmation and audit, and “judging people by their appearance” is in line with the law of human cognition. High recognition accuracy and speed Compared with other biometric technologies, the recognition accuracy of face recognition technology is at a high level, and the false recognition rate and rejection rate are low.
In applications with high security requirements, face recognition technology requires the recognition object to be physically present at the recognition site, making it difficult for others to counterfeit. The unique active discrimination ability of face recognition technology ensures that others cannot cheat the recognition system with inactive photos, puppets or wax figures. This is difficult to do with biometric technologies such as fingerprints. For example, the identity of a legitimate user can be impersonated by a severed finger of a legitimate user without the identification system being able to detect it. The equipment used by face recognition technology is general PC, camera and other conventional equipment, because the computer, closed-circuit television monitoring system and so on have been widely used, so for most users to use face recognition technology without adding a lot of special equipment, thus not only protecting the user’s original investment but also expanding the function of the user’s existing equipment, to meet the user’s security needs.
The basis information is easy to obtain face recognition technology is based on the face photo or the face image taken in real time, so it is undoubtedly the easiest to obtain. Low cost, easy to promote the use of face recognition technology because the use of conventional general equipment, the price are in the general user acceptable range, compared with other biometric technology, face recognition products have a very high performance to price ratio. In summary, face recognition technology is a high-precision, easy to use, high stability, difficult to counterfeit, cost-effective biometric identification technology, with extremely broad market application prospects.
face recognition device
Face recognition is considered to be one of the most difficult research topics in the field of biometric recognition and even in the field of artificial intelligence. The difficulties of facial recognition are mainly brought about by the characteristics of the face as a biometric feature. Similarity is not very different between different individuals, all faces have similar structures, and even the structural appearance of facial organs is similar. Such characteristics are advantageous for localization using the face, but unfavorable for differentiating human individuals using the face. In addition, facial recognition is affected by many factors such as lighting conditions (e.g., day and night, indoor and outdoor, etc.), many coverings of the face (e.g., masks, sunglasses, hair, beard, etc.), and age.
In facial recognition, the first class of variations is supposed to be enlarged and used as a criterion to distinguish individuals, while the second class of variations should be eliminated because they can represent the same individual. The first type of variation is usually referred to as interclass variation, while the second type of variation is referred to as intraclass variation. For faces, intra-class variation is often greater than inter-class variation, thus making it exceptionally difficult to distinguish individuals using inter-class variation when disturbed by intra-class variation.
Face recognition system mainly includes four components, which are: face image acquisition and detection, face image pre-processing, face image feature extraction, and matching and recognition.
1. Face image acquisition:
Different face images can be captured through the camera lens, such as static images, dynamic images, different positions, different expressions and other aspects can be well captured. When the user is within the shooting range of the acquisition device, the acquisition device will automatically search and shoot the user’s face image. Face detection: Face detection is mainly used in practice for pre-processing of face recognition, i.e., to accurately calibrate the position and size of a face in an image. The face image contains rich pattern features, such as histogram features, color features, template features, structure features and Haar features. Face detection is to pick out the useful information from these and use these features to achieve face detection.
2. Face image pre-processing:
Image pre-processing for faces is the process of processing images based on face detection results and eventually serving for feature extraction. The original image acquired by the system is often not directly usable due to various conditions and random interference, and must be pre-processed at an early stage of image processing, such as grayscale correction, noise filtering and other image pre-processing. For face images, the pre-processing process mainly includes light compensation, grayscale transformation, histogram equalization, normalization, geometric correction, filtering and sharpening of face images. 3.
Face image feature extraction: The features that can be used in face recognition system are usually divided into visual features, pixel statistical features, face image transformation coefficient features, face image algebraic features and so on. Face feature extraction is performed for certain features of the face. Face feature extraction, also known as face characterization, is the process of feature modeling of faces. The methods of face feature extraction are summarized into two categories: one is knowledge-based characterization methods; the other is algebraic feature-based or statistical learning characterization methods.
Face image matching and recognition: The extracted feature data of the face image is searched and matched with the feature template stored in the database by setting a threshold value, and when the similarity exceeds this threshold value, the matched result is output. Face recognition is to compare the features of the face to be recognized with the obtained face feature template, and to judge the identity information of the face according to the degree of similarity. This process is divided into two categories: confirmation, which is a one-to-one image comparison process, and recognition, which is a one-to-many image matching comparison process.