Color face recognition method based on semi-supervised multi-view incremental dictionary learning

Abstract

The invention discloses a color face recognition method based on semi-supervised multi-view incremental dictionary learning, and belongs to the technical field of face recognition. The method fully utilizes an incremental learning technology, and comprises the steps of dividing a training stage into two sub-stages of a training sample set and dictionary initialization stage and a training sample set and dictionary updating stage; at the training sample set and dictionary initialization stage, using an initial color face image training sample set to carry out dictionary learning in a mode the same as that of a color face recognition method based on semi-supervised multi-view dictionary learning to obtain an initial dictionary; at the training sample set and dictionary updating stage, according to the change of the color face image training sample set, simply modifying the learned dictionary, and then carrying out dictionary updating. Compared with the color face recognition method basedon the semi-supervised multi-view dictionary learning, when the color face image training sample set changes, the training time consumed for updating the dictionary can be greatly shortened.

Description

technical field [0001] The invention belongs to the technical field of face recognition, in particular to a color face recognition method based on semi-supervised multi-view incremental dictionary learning. Background technique [0002] Patent application number 201710800074.7 The objective function of the color face recognition method based on semi-supervised multi-view dictionary learning is defined as follows: [0003] [0004] [0005] Among them, X R 、X G 、X B Respectively represent the R, G, B color component training sample sets of the color face image training sample set, X Rl 、X Gl 、X Bl Respectively represent the R, G, B color component training sample sets with category marks, c represents the number of categories of color face image training samples with category marks, X ip means X il In the sample of the pth class, X Ru 、X Gu 、X Bu Respectively represent the R, G, B color component training sample sets without class labels, D i Indicates that t...

AI Technical Summary

Problems solved by technology

Once the color face image training sample set changes, such as adding or updating a small number of color face image training samples, the color face recognition method based on semi-supervised multi-view dictionary learning needs to re-run the entire dictionary learning process to re-learn all dictionaries, Cannot make full use of the learned dictionary to reduce the training time spent updating the dictionary

Images