Semi-supervised multi-view dictionary learning based color face recognition method

Abstract

The invention discloses a semi-supervised multi-view dictionary learning based color face recognition method. According to the method, a multi-view leaning technology is applied to semi-supervised color facial image dictionary learning. In the training stage, by learning structured dictionaries of all chrominance components separately and making the dictionaries be orthogonal to one another, the correlation among all the chrominance components is removed, and complementary difference information among all the chrominance components is fully utilized; in the dictionary learning process, class-label-free color facial image samples are used for participating in training, and all training sample information is fully utilized. In the class test stage, all the chrominance components are added up, the dictionary corresponding to each class of training samples is used for reconstructing reconstruction errors of test samples, and finally the test samples are classified as the class with the smallest accumulative reconstruction error. Accordingly, the recognition effect is higher, and by means of semi-supervised multi-view dictionary learning, the color face recognition capacity is obviously enhanced.

Description

technical field [0001] The invention specifically relates to a color face recognition method based on semi-supervised multi-view dictionary learning, and belongs to the technical field of face recognition. Background technique [0002] (1) K singular value decomposition 2 color extension 2 method with consistent labels (CE2-LC-KSVD2, Shi Jinglan, Chang Kan, Zhang Zhiyong, Qin Tuanfa, "Dictionary Learning Algorithm for Color Image Face Recognition", Telecommunications Technology, 56( 4): 365-371, 2016): [0003] For a color face image training sample set X, let n represent the number of all color face image training samples, c represent the category number of all color face image training samples, X R ∈R d×n 、X G ∈R d×n 、X B ∈R d×n Respectively represent three color component sample sets of R, G and B, and d represents the dimension of color component samples. The objective function of CE2-LC-KSVD2 method is [0004] [0005] Among them, X'=(I+γ / d·E)[X R ;X G ;X ...

AI Technical Summary

Problems solved by technology

[0007] Although the CE2-LC-KSVD2 method uses the correlation between the color channels by modifying the inner product calculation criterion of the orthogonal matching pursuit algorithm in the sparse coding stage, this modification only forces the selected dictionary atoms to consider the average color and does not make full use of it. Color information for color images

In addition, the CE2-LC-KSVD2 method is a supervised dictionary learning method, which can only use class-labeled color face image samples in the training stage, and cannot make full use of the large number of non-class-labeled color face image samples

Images