Face recognition feature extraction algorithm based on local cyclic graph structure

Abstract

The invention relates to a face recognition feature extraction algorithm based on a local cyclic graph structure. The algorithm is mainly characterized by selecting a 3 * 3 neighborhood in a face grayscale image and setting corresponding pixel values; cyclically constructing a graph structure in the selected neighborhood in a certain order; successively comparing the pixel values according to the order of the graph structure along the direction of an arrow, and expressing a result in binary; and calculating the characteristic value of the central pixel in the neighborhood. The algorithm is reasonable in design, can accurately describe facial features, provides the obtained characteristic value of the target pixel with more representativeness, and improves a recognition rate. The obtained characteristic value describes the characteristic information of a facial image comprehensively so as to be capable of face recognition. Further, the algorithm has advantages over a symmetrical local graph structure algorithm based on multi-directional weight optimization in terms of time consumption.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a face recognition feature extraction algorithm (LCGS) based on a local cycle graph structure. Background technique [0002] A complete face recognition system includes three modules: object detection, feature extraction and face recognition. Among them, whether effective facial feature information can be extracted is a very important step. There are many algorithms for extracting facial features, which can be roughly divided into two types based on global features and based on local features. Studies have shown that the extraction method based on local features is slightly higher than the extraction method based on global features in terms of recognition rate. In 2011, inspired by the dominating set in the graph structure, Abusham et al. applied it to face feature extraction and proposed the local graph structure operator (LGS). This operator extracts 5 pixels around...

AI Technical Summary

Problems solved by technology

[0004] However, LGS and MOW-SLGS respectively take 3×4 and 5×5 neighborhoods when performing neighborhood division, but when calculating eigenvalues, they do not use all the information of surrounding pixels in the neighborhood, resulting in information loss. As a result, the final face recognition effect is not ideal.

Images