Low-resolution face recognition method coupling gait characteristics

Abstract

The invention provides a low-resolution face recognition method coupling gait characteristics. The method includes that all low-resolution faces and gait samples are converted to a vector space, core transformation characteristics of faces and the gait characteristics are calculated by adopting inner product and revised, then low-resolution face images and gait samples indicating the same individual form sample pairs, sample pairs under different collections are close enough, essence geometrical characteristics of a data local structure are kept, a goal optimization model is built and transformed into marks to resolve generalized characteristics to obtain two different transformation matrixes, and the low-resolution face images and gait images obtain new characteristics. During testing, a testing sample vectors first and is mapped to a high-dimensional space from the vector space through the core transformation, and an affiliation category is predicted by adopting the nearest neighbor sorter. The method does not need to estimate high-resolution face images and can conduct identity recognition directly by using a gait coupling machine study method on the low-resolution face images.

Description

technical field [0001] The invention relates to a low-resolution face recognition method coupled with gait features, and belongs to the technical field of pattern recognition. Background technique [0002] Low-resolution face recognition at a long distance is one of the challenging research problems in biometric recognition technology. Because low-resolution face images can only provide relatively limited information, the recognition performance of face recognition is poor. . A potential method to improve the recognition accuracy is to reconstruct a high-resolution face image from a low-resolution face image. A super-resolution implementation method based on manifold alignment proposed in [1] can improve the accuracy of face images. resolution. Huang Hua et al. [2] used canonical correlation analysis to establish a consistent subspace of low-resolution face images and high-resolution face images, and then in the high-resolution face image features and low-resolution face i...

AI Technical Summary

Problems solved by technology

However, most of the existing super-resolution algorithms are not effective in dealing with low-resolution face recognition problems, because the similarity in the feature space of low-resolution face images is difficult to reflect the real similarity[3]

Images