Face recognition method based on multi-resolution multi-threshold local binary pattern

Abstract

The invention discloses a face recognition method based on the multi-resolution multi-threshold local binary pattern, and pertains to the technical field of pattern recognition. Through the local binary pattern, spatial structure information of positions of face facial organs is hard to acquire, and at the same time, the LBP operator adopts size relationship between local region neighbour pixels and the central pixel to perform encoding, so the noise effect exists; in order to solve the problems, the method adopts different thresholds to perform LBP image encoding, and finally, face local and overall information is acquired through different division methods, so the MRTLBP characteristic information extraction is more discriminative. The characteristics are used as the face discrimination characteristics for classification and recognition. Classification and recognition are performed by adopting nearest neighbor classification devices. The experimental analysis shows that the method of the invention has good face characteristic expressing capability and has high robustness for illumination, expressions and poses.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a face recognition method based on a multi-resolution multi-threshold local binary pattern (LBP). Background technique [0002] Face recognition is a typical research topic in the fields of pattern recognition, image analysis and understanding, etc. It not only has important theoretical value, but also has important application prospects in security, financial and other fields, so it has been widely received in academia and industry. At present, some practical commercial systems have emerged. However, due to changes in the image acquisition conditions and the attributes of the face itself, the appearance of different photos of the same person may vary greatly, which increases the difficulty of recognition. Therefore, improving the robustness of face recognition systems to these changes has become one of the important goals of researchers in this field. [0003] Wave...

AI Technical Summary

Problems solved by technology

[0012] 1. The traditional LBP operator is encoded by comparing the size relationship between the neighbor pixels and the center pixel in the local area, which is easily affected by noise;

[0013] 2. The local binary mode is difficult to obtain the spatial structure information of the face. These spatial structure information mainly refer to the positional relationship of the facial organs of the face, such as eyes, nose, mouth, etc., by dividing the face image into different scale modes, That is to say, the fusion of local spatial information and these global spatial information is a factor that needs to be considered in face recognition;

Images