Face recognition method based on extraction of multiple evolution features

Abstract

The invention discloses a face recognition method based on extraction of multiple evolution features. The method comprises the steps as follows: (1), classification of initial samples: the initial samples are divided into three parts, including training samples for feature extraction, training samples for weight evolution and test samples respectively; (2), feature extraction of the training samples: the training samples are subjected to feature extraction with a multiple seed space method, such as PCA (principal component analysis), LDA (linear discriminant analysis), LPP (locality preserving projection) or the like; and (3), multiple feature fusion evolution: features obtained with different feature extraction methods are fused according to a form that Phi is equal to the sum of Omega 1 Phi 1, Omega 2 Phi 2, ..., and Omega n Phi n, and the like, wherein Omega is a weight coefficient. An optimal weight coefficient is obtained with a genetic algorithm, so that fused features have better recognition effects than prior features. The face recognition method has the advantages that the principle is simple, the method is unique, the application is easy, and the like.

Description

technical field [0001] The invention mainly relates to the fields of feature extraction and face recognition, in particular to a face recognition method based on evolutionary multi-feature extraction suitable for a face recognition system. Background technique [0002] Currently, the successful application of facial image recognition analysis and understanding has received significant attention. However, there are still many challenges in implementing a face recognition system in the real world. One of the main challenges faced is the "curse of dimensionality" problem, a pervasive problem in pattern recognition. It points to the fact that, at the cost of increasing data size, the sample estimates required to accurately represent the data grow exponentially. The spatial resolution of face images is at least hundreds of pixels, sometimes tens of thousands. From a statistical point of view, this will require tens of thousands of face samples to deal with the problem of face ...

AI Technical Summary

Problems solved by technology

However, the common shortcomings of these methods are obvious, just like the problems of PCA and LDA, 2DPCA and 2DLDA cannot take into account the spatial relationship between two samples, and can only see the global Euclidean structure

2DLPP only considers the manifold structure of the local image space, which can effectively maintain the local structure, but it cannot be generalized globally

Images