A Face Recognition Method Based on Dimensionality Reduction Based on Multi-core Association Integration

Abstract

The invention discloses a face recognition method based on multi-core correlation integration and dimensionality reduction. The method comprises the following steps: preprocessing face picture data, obtaining a training sample matrix, and performing data dimensionality reduction processing on the data sample matrix by using multi-core correlation integration; The weight of each kernel model is determined according to the eigenvalues ​​and eigenvectors, so as to weight the matching classifier, thus solving the problem of high dimensionality and difficult processing of the original data of face recognition, and the need to select a kernel in the dimensionality reduction method of typical association analysis based on kernels The problem of the function and the parameters in the function can be obtained to obtain a higher face recognition rate, which can shorten the matching time and reduce the matching difficulty, so that the face recognition process will be more accurately realized and a higher recognition accuracy rate can be obtained.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a face recognition method based on multi-core association integration and dimensionality reduction. Background technique [0002] With the rapid development of information technology, people hope to confirm the identity of a person more efficiently and automatically. The characteristic information possessed by each person is very different and has great differences, so it can be used for identity verification. Face recognition technology has become a popular research technology, and its research and application are becoming more and more important. With the deepening of the research, it has also received wider attention from the society. In recent years, as an important part of biometric identification, it has been widely used in video surveillance, human-computer interaction, multimedia management and other fields, such as security checks for important occasions, rea...

AI Technical Summary

Problems solved by technology

[0006] According to the deficiencies and defects of the prior art, the present invention proposes a face recognition method based on multi-core association integration dimensionality reduction, the purpose is to solve the problem of high dimensionality and difficult processing of the original data of face recognition, and the typical association based on kernel Analyze the problem of selecting the kernel function and parameters in the function in the dimensionality reduction method, so as to obtain a higher face recognition rate

Images