Weighted sparse representation human face recognition method and system based on sparse coefficient similarity

Abstract

The invention discloses a weighted sparse representation human face recognition method based on sparse coefficient similarity. The method comprises the following steps of preprocessing human face training sample images and test samples to construct a training sample matrix; defining Euclidean distance negative exponential function mapping values of column vectors of the training samples and the test samples as weights to construct a weight matrix; calculating sparse coefficients of all the training samples and the test samples; according to the similarity between the sparse coefficients of thetraining samples and the test samples, selecting K samples adjacent to the test samples through cosine similarity to form an adjacent sample matrix; solving the sparse coefficients of the test samples by adopting an L1 norm least square method; and reconstructing residual errors of the test samples to realize classification. According to the method and a system, the locality and sparsity of training sample data are utilized, so that a recognition algorithm is more stable, excessive selection of other types of samples is avoided, and the classification accuracy of the test samples is improved.The human face recognition method can be used for performing human face recognition, and has relatively good market prospects.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method and system based on weighted sparse representation based on sparse coefficient similarity. Background technique [0002] As a recognition technology based on physiological characteristics in the field of biometrics, face recognition technology is a technology that extracts the features of the face through a computer and performs identity verification based on these features. Faces are born with fingerprints, iris, voice, etc., and their uniqueness and good characteristics that are not easy to be copied provide the necessary premise for identification; compared with other biometric technologies, face recognition The technology has the advantages of simple operation, intuitive results, good concealment, and avoiding direct contact. Therefore, face recognition has broad application prospects in information security, criminal detection, access cont...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to address the deficiencies in the prior art and provide a weighted sparse representation face recognition method based on similar sparse coefficients. To solve the problems of poor stability of existing algorithms, large amount of calculation, and insufficient correlation of local features

Images