Weighted multi-task sparse representation three-dimensional face recognition method and system and medium

Abstract

The invention discloses a weighted multi-task sparse representation three-dimensional face recognition method and system and a medium, and the method comprises the following steps: dividing a three-dimensional face into a plurality of different regions which comprise a semi-rigid region and a non-rigid region and have different weights; extracting curve features of different areas of the three-dimensional face; and based on the curve features, performing recognition matching on the three-dimensional face by adopting a weighted sparse representation algorithm. Compared with the prior art, the method and the system and the medium have the advantages that the influence of expression change on different areas of the three-dimensional face on three-dimensional face recognition is reduced, and the robustness of three-dimensional face recognition is improved.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a three-dimensional face recognition method, system and medium based on weighted multi-task sparse representation. Background technique [0002] 3D face recognition has undergone great changes in technology since it was proposed, but it can be divided into two major stages in terms of technology. In the early days, 3D face recognition mainly focused on the entire 3D face. The geometric information of the entire 3D face is used as a feature, and it will not be subdivided. For any two 3D faces, the feature similarity of the entire face is usually calculated. The algorithms at this stage are collectively referred to as 3D face based on overall features. Face recognition algorithms, common methods are based on principal component analysis, deformation model, signed shape differential map, spherical harmonic function, etc. The other stage is the algorithm that is mai...

AI Technical Summary

Problems solved by technology

[0006] However, the geometric information on the 3D face will also have a large deformation when the expression changes, resulting in a large difference in the calculation results of the same area. On the same 3D face, different areas are also affected by the deformation of the expression change. There is a big difference, so the expressive and non-expressive areas on the 3D face have a great impact on the algorithm recognition

Images