Face identification method based on texture feature fusion and SVM

Abstract

The invention provides a face identification method based on texture feature fusion and an SVM, which belongs to the image processing field. The method comprises the following steps of firstly using a uniform LBP operator to extract NSCT transformation multi-scale multi-direction high-frequency sub-band texture features, and counting and further combining the uniform mode LBP feature information of each high-frequency sub-band to acquire a face texture feature ULNBH combining advantages of both the LBP operator and the NSCT. The ULNBH is lack of low frequency information. Therefore, the ULNBH feature and a Gabor feature are fused in a feature layer by using the characteristics of the Gabor feature to acquire a fusion feature with more complete face texture feature information. During a face identification stage, a principal components analysis (PCA) method is adopted to perform dimension reduction on high-dimension characteristic vectors. The SVM is further adopted to identify the fusion feature with the dimension reduced. The fusion feature has greater robustness relative to illumination and posture changes.

Description

technical field [0001] The invention relates to a face recognition method, which belongs to the field of image processing, in particular to a face recognition method based on texture feature fusion and SVM. Background technique [0002] In recent years, with the rapid development of Internet technology, information technology has brought great influence to all fields of the whole society. In the general application of information technology, security issues are related to all aspects of people's life. Identity authentication technology is a very critical component in the field of information security. Traditional identity authentication technologies mainly use passwords and smart cards, which have potential safety hazards that are easy to be stolen and lost. As a kind of biometric technology, face recognition technology is a comprehensive technology that combines computer technology, iconography, statistics and physiology to accurately verify and identify certain stable fea...

AI Technical Summary

Problems solved by technology

[0003] The rapid development of the fields of computer science and image processing has greatly promoted the research of face recognition. However, due to the fact that there are often various interferences in the actual face image acquisition and processing process, the effect of face recognition is greatly affected. Especially in the process of face image acquisition, it is often disturbed by factors such as illumination changes and changes in face posture, so that the extracted face feature information is not comprehensive enough or mixed with too much redundancy. The remaining information has a very bad impact on the final face recognition effect

Various experts and scholars have proposed many targeted solutions to the current problem of illumination or attitude changes in face recognition. Although the influence of a single interference factor in illumination changes or attitude changes has been weakened, the coexistence of these two interference factors However, the effect of face recognition still needs to be improved, so it is of great significance to further study the face recognition system under illumination interference and posture changes.

Images