Method and device for detecting and identifying human face applied to set environment

Abstract

A human face detection and identification method and device applies for the specified environment, including a camera module, a video synchronization capture module, a face detection module, a face identification module and a personnel database module. The main method is that the video synchronization capture module synchronized captures the facial images photographed by the camera module, and then the face detection module detects the presence of facial features in the images, and if facial features are acknowledged, the images are sent to the face identification module to do the facial feature extraction, and compared with the human facial information of the personnel database module, and finally, the legal / illegal person identification result is generated.

Description

technical field [0001] The present invention relates to a method of capturing facial images at different angles under a set environment, and using image processing technology to detect and extract facial features at different angles for the images at different angles. According to the obtained results, there are A method and device for flexibly integrating and judging whether a face condition is met or a specific person's facial features is applied to face detection and recognition in a set environment. Background technique [0002] The current biometric face recognition system uses a camera to capture a frontal image of a person's face, or uses a camera to capture one or more frontal images of a person's face from a series of video recordings of face images. For this one or more frontal images of faces, use image processing methods to extract face features, compare them with the previously established face image database, and finally output the recognition results; however,...

AI Technical Summary

Problems solved by technology

[0002] The current biometric face recognition system uses a camera to capture a frontal image of a person's face, or uses a camera to capture one or more frontal images of a person's face from a series of video recordings of face images. For this one or more frontal images of faces, use image processing methods to extract face features, compare them with the previously established face image database, and finally output the recognition results; however, a single camera with a single angle shoots a The method of one or more frontal images of human faces cannot overcome the problem that intruders can deceive the camera and recognition system by wearing a mask, put heavy makeup on the user or change the hairstyle to cover part of the face, causing the features to disappear or the extracted features to be consistent with the recognition system. Inconsistencies in the database may easily lead to misjudgment; in addition, if the system is used in outdoor or semi-outdoor places, it often encounters the problem of light changes. Backlighting or changes in light angles can easily cause facial feature extraction failures and errors, resulting in facial features. Decreased resolution

Images