Three-dimensional face recognition method based on feature points

Abstract

The invention relates to the technical field of face recognition, and discloses a three-dimensional face recognition method based on feature points. The three-dimensional face recognition method comprises the following steps: S1, face image processing; S2, face feature value extraction; and S3, face feature value comparison, wherein the face image processing comprises the steps of preprocessing the face of a user, and extracting feature regions of a to-be-identified sample and a basic sample; establishing a corresponding human face three-dimensional point diagram according to the extracted feature region, and performing human face region detection according to the two-dimensional human face point diagram corresponding to the human face three-dimensional point diagram; and synchronously establishing a transfer coordinate system. According to the three-dimensional face recognition method based on the feature points, data modeling is conducted on a face in a three-dimensional mode, and the face is preprocessed through Delaunay triangular mesh data, and the influence of posture and expression changes on recognition is overcome to a certain extent through a face posture correction method based on Hadoop model transformation and the like.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a three-dimensional face recognition method based on feature points. Background technique [0002] Face recognition is a biometric identification technology based on human facial feature information; use a camera or camera to collect images or video streams containing human faces, and automatically detect and track human faces in the images, and then detect A series of related technologies for face recognition. [0003] At present, the importance of face recognition has been paid more and more attention with the development of intelligence. How to ensure the accuracy and security of face recognition is one of the problems that people have been working hard to solve; The interference of external factors such as light and makeup leads to the problem of recognition errors. At the same time, due to the irregularities of faces and the uncertainty of expressions, it is diffic...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies in the prior art, the present invention provides a three-dimensional face recognition method based on feature points, which has the advantages of overcoming the influence of posture and expression changes on recognition to a certain extent, and solves many problems in traditional face recognition. There are problems of recognition errors caused by the interference of external factors such as light and makeup. At the same time, due to the irregularities of faces and the uncertainty of expressions, it is difficult to improve the recognition effect of face recognition.