Three-dimensional face recognition method based on vertical and horizontal local binary pattern on the mesh

Abstract

The invention discloses a three-dimensional face recognition method based on a vertical and horizontal local binary pattern on the mesh. The method comprises: pretreatment including face region cutting, smoothing processing, and pose normalization is carried out on a three-dimensional face model and all faces are placed under a pose coordinate system; seven profile lines of a face is extracted from a semi-rigid region of the three-dimensional face model and uniform resampling is carried out on each profile line to obtain 28 key points to represent a facial curved surface; surrounding adjacent regions of the key points are extracted, adjacent regions of the key points are represented by using a descriptor of a vertical local binary pattern on the mesh and a descriptor of a horizontal local binary pattern on the mesh, feature fusion is carried out to obtain a descriptor of a vertical and horizontal local binary pattern on the mesh; and then a 3D face is identified by using an LC-KSVD2 dictionary learning classification algorithm. According to the invention, local shape changes of a uniform face mesh surface due to factors like an expression can be described comprehensively; and the identification performance is excellent.

Description

technical field [0001] The present invention relates to a three-dimensional face recognition method based on grid vertical and horizontal local binary patterns, in particular to a face recognition method that uses face grids to directly recognize faces in the 3D field, and is suitable for people with large occasions of change. Background technique [0002] In the past two decades, the accuracy and applicable occasions of face recognition have been greatly limited due to the vulnerability of two-dimensional face recognition methods in the face of posture, different lighting conditions, expression changes, and facial makeup. More and more scholars have begun to devote themselves to the research of 3D face recognition technology. Three-dimensional face recognition technology refers to the technology of using the geometric information of the face in three-dimensional space for identity recognition. At present, many scholars have proposed many effective 3D face recognition meth...

AI Technical Summary

Problems solved by technology

[0003] At present, many 3D face recognition algorithms are based on Local Binary Pattern (LBP, Local Binary Pattern), but most of these algorithms will convert the 3D point cloud of the face into a depth map and then improve and expand the LBP. The 3D data is converted to 2.5D, and part of the face information is lost

Images