Human face recognition method and device for quickly processing human face shading

Abstract

The invention discloses a human face recognition method and device for quickly processing human face shading, and the method comprises the steps: obtaining a test human face sample and a standardized learning dictionary; solving a local restriction code of an unshaded part of the test human face sample through employing a target function with the local restriction, and modeling a shaded region of the test human face sample through a Markov random field till the detection is completed; obtaining the sparse representation of the unshaded part of the test human face sample through the target function with l2-normal constraint; generating a reconfigured human face, corresponding to each class, class by class, and solving a reconfiguration error between the reconfigured human face of each class and the test human face sample; searching a corresponding class with the minimum reconfiguration error, determining the class as the class of the test human face sample, and outputting the class. The method can process and recognize a human face which is shaded or polluted by noise, is higher in recognition speed under the condition of guaranteeing the recognition success rate, achieves the better recognition of the human face, and is more suitable for an actual scene.

Description

technical field [0001] The invention relates to the technical field of computer vision and pattern recognition, in particular to a face recognition method and device for quickly processing face occlusion. Background technique [0002] At present, face recognition is one of the hot research issues in the field of computer vision and pattern recognition, and the occlusion problem has become an important and difficult problem in the field of face recognition due to its diversity. [0003] John Wright et al. proposed the Sparse Representation-based classification (SRC) method in 2009. This method believes that each test face image can be linearly combined with the same category of face images in the training sample set. To represent. Therefore, ideally, the encoding coefficients corresponding to training samples of other categories are zero, while the encoding coefficients corresponding to training samples of the same category as the test face samples are not zero, which reflec...

AI Technical Summary

Problems solved by technology

There are two problems in doing this: (1) The new dictionary has a large number of columns, and it is very time-consuming to solve the sparse coefficient of the test face image on this new dictionary (2) This method cannot solve the continuous occlusion problem well

However, the computational complexity of SEC_MRF is very large, it needs to iteratively solve l 1 Norm minimization problem, so the calculation speed is relatively slow, not suitable for real-time scenarios

Images