Super-resolution face recognition method based on multi-manifold discrimination and analysis

Abstract

Disclosed is a super-resolution face recognition method based on multi-manifold discrimination and analysis. During the training phase, a mapping matrix from a low-high-resolution face image multi-manifold space to a high-resolution face image multi-manifold space is acquired by multi-manifold discrimination and analysis. An intra-class similar graphs and aninter-class similar graph are constructed in an original high-resolution face image multi-manifold space, a discrimination bound term is constructed by utilizing the two neighbor graphs, and a most optimization method is to acquire the mapping matrix by reconstructing a cost function composed of a bound term and the discrimination bound term. During the recognition phase, a low-resolution face image to be recognized is mapped o the high-resolution face image multi-manifold space by the mapping matrix acquired by offline learning, and a high-resolution face image is acquired. Classification and recognition are achieved by a nearest-neighbor classifier according to the Euclidean distance principle in the high-resolution face image multi-manifold space. Compared with a traditional super-resolution method, the super-resolution face recognition method has greatly improved face recognition rate and operation rate.

Description

field of invention [0001] The invention relates to a face recognition method, in particular to a face recognition method based on multi-manifold discriminant analysis super-resolution. Background technique [0002] As an important biometric method, face recognition has received a lot of attention in both research and marketing fields in the past three decades. However, in many cases, due to the long distance between the camera and pedestrians, the resolution of the captured face image is too low, and the face image loses too much detail information, which makes it difficult to be effectively identified by humans or machines. . Therefore, how to perform matching and recognition of low-resolution face images has become a problem that needs to be further solved in current face recognition technology. [0003] Low-resolution face recognition methods are roughly divided into two categories. One method is to directly down-sample the images in all face databases to the same size ...

AI Technical Summary

Problems solved by technology

However, the ultimate goal of face super-resolution is for reconstructed face recognition. The face images reconstructed by traditional face super-resolution methods lack discriminative information useful for face recognition.

Images