An Adaptive Dictionary Construction Method for Sparse Representation Face Recognition

Abstract

The invention discloses a self-adaptive dictionary construction method for sparsely represented face recognition, including acquiring a face image to be tested and several face image samples, storing several face image samples into a training sample set, and extracting a face image to be tested and the LCP feature of each sample in the training sample set; obtain the average LBP feature similarity and the average MiC feature similarity between the face image to be tested and all samples in the training sample set; judge whether the LBP feature and the MiC feature are legal features, if LBP Neither the feature nor the MiC feature is a legal feature, then refuse to recognize the face image to be tested; otherwise, go to the next step; in the legal feature, when the LBP feature similarity is not less than the LBP feature neighbor threshold and the MiC feature similarity is not greater than the MiC feature When the neighbor threshold is set, the corresponding samples in the training sample set are marked as the neighbor samples of the face image to be tested; the marked neighbor samples of the face image to be tested are used as atoms to construct an adaptive face recognition redundant dictionary.

Description

technical field [0001] The invention belongs to the field of face recognition, and in particular relates to an adaptive dictionary construction method for sparse representation face recognition when a classification-based sparse representation algorithm is adopted. Background technique [0002] Face recognition is a technology that uses people's facial images for identity recognition, and has broad application prospects in economic, civil, military, public security and other fields. Sparse representation utilizes an over-complete redundant dictionary to perform an optimal linear representation of the input test data, and the representation coefficients are sparse vectors. Classification-based sparse representation algorithms are a class of algorithms that use sparse representation vectors and various training samples to reconstruct and classify test data class by class. A large number of literatures show that classification-based sparse representation algorithms have a high...

AI Technical Summary

Problems solved by technology

First, increase the number of atoms to increase the sparsity of the representation vector to improve the recognition rate, but the calculation speed of any sparse solution algorithm will decrease as the number of atoms increases

Second, for any input test image, the redundant dictionary is fixed and not adaptive

Images