Multi-pose face recognition method based on hidden least square regression and device thereof

Abstract

The invention discloses a self-adaption multi-pose face recognition method based on hidden least square regression. The self-adaption multi-pose face recognition method includes the multi-pose face recognition method based on the hidden least square regression. The method includes the steps of detecting a region size and a region position of an input facial image; correcting the detected facial image, obtaining a corrected facial image; extracting facial characteristic values from the corrected facial image; estimating a pose type of the corrected facial image according to the extracted facial characteristic values; selecting a corresponding transformational matrix of a pose type and a corresponding offset vector of the pose type according to the pose type, and calculating to obtain an identity characteristic vector of the facial image according to the transformational matrix, the offset vector and the extracted identity characteristic vector; and searching for a known facial image which has the highest similarity with the identity characteristic vector of the input facial image in a known facial image search library, and returning identity information of the known facial image to be used as a recognition result.

Description

Technical field [0001] The invention belongs to the technical field of computer-based pattern recognition, and specifically refers to an adaptive multi-posture face recognition method and device based on hidden least square regression. Background technique [0002] Face recognition technology is an attempt to give a computer human-like visual perception function, that is, to identify the identity of other people based on faces. The research on face recognition began in the middle and late 1960s, and has been developed in the past 50 years. Especially in the past decade, it has become a hot research topic. Facial recognition is valued because of its important academic research significance and huge potential application prospects. Face recognition is a typical image pattern analysis, understanding and classification calculation problem, which includes pattern recognition, image processing, analysis and understanding, computer vision, artificial intelligence, human-computer intera...

AI Technical Summary

Problems solved by technology

Using 3D image acquisition equipment to obtain the 3D structure of the face is the most direct method, but the cost of the equipment is high and requires the cooperation of the user, thus limiting the scope of application

On the other hand, in most practical applications, the collected images are two-dimensional images, and the three-dimensional shape of the face can be accurately reconstructed from the two-dimensional image, especially the reconstruction of the three-dimensional face from a single two-dimensional image. The amount is large and the difficulty is also very large

Images