3D (Three-Dimensional) face recognition method

Abstract

The invention relates to a 3D (Three-Dimensional) face recognition method. A face position correction method of positioning eyes in a face gray level image is adopted by the method, and the method is used for quickly and effectively correcting single face gray level image visible to double eyes and accurately determining pupil positions of the double eyes in the correction result to realize quick positioning according to the human eye gray level change characteristics, human eye geometric shape characteristics and axisymmetric characteristics of the double eyes; and in a characteristic extraction and recognition process, a principal component analysis face image recognition method of BP (Back-Propagation) neural network is adopted, the method is used for extracting face characteristics (vectors) from the face image through a non-linear principal component analysis neural network and recognizing the face image on the BP neural network, thereby improving the recognition efficiency, and the method is reliable in effectiveness and stability.

Description

technical field [0001] The invention relates to a face recognition method, in particular to a 3D face recognition method. Background technique [0002] Face recognition, specifically refers to the computer technology that uses the analysis and comparison of facial visual feature information for identity identification. Face recognition is a popular computer technology research field, face tracking detection, automatic adjustment of image magnification, night infrared detection, automatic adjustment of exposure intensity; ) Its own biological characteristics to distinguish individual organisms. In the process of face recognition, it usually includes the following three steps: face detection and tracking, location and registration of key facial feature points, extraction and comparison of face features, and registration of face features, which have a significant impact on the recognition rate. big impact. At the same time, the positioning of eyes is the basis for the po...

AI Technical Summary

Problems solved by technology

[0003] At present, the two-dimensional face recognition technology is mature, but the two-dimensional face recognition is based on the plane image of the face. In fact, the face itself is three-dimensional, and the plane image of the face is just the projection of the three-dimensional face on a plane. In this In the process, some information will inevitably be lost, so the recognition rate needs to be further improved; while the face reconstruction algorithm in 3D face recognition technology is very complicated, and the recognition speed is relatively slow.

Images