One-shot Face Recognition Method Based on Sparse Representation of Hybrid Extended Block Dictionary

Abstract

The invention discloses a single-sample face recognition method based on the sparse representation of a hybrid extended block dictionary, which includes step (S1): constructing a general data set X of non-target objects; step (S2): constructing a standard sample set N of target objects; Step (S3): Construct the test sample set Y; Step (S4): Construct the occlusion block dictionary and intra-class difference block dictionary of non-target objects Step (S5): The mixed and complete extended block dictionary obtained according to the above steps adopts the The weighted block sparse representation classifier performs linear sparse representation on the B block images of the target object sample y to be tested, so as to perform occluded face recognition of the sample to be tested. In the present invention, the face image is divided into blocks first, and then the basic block dictionary of the target object, the occlusion block dictionary of the non-target object and the intra-class difference block dictionary are respectively constructed by using the KDA algorithm, and finally the weighted block sparse representation classifier is used to accurately classify the samples to be tested. prediction, which effectively improves the accuracy of single-sample face recognition.

Description

technical field [0001] The invention relates to the technical field of single-sample face recognition in which only one or a small number of standard samples are identified in human-computer interaction, and in particular to a single-sample face recognition method based on the sparse representation of a hybrid extended block dictionary. Background technique [0002] In recent years, due to the rapid development of technologies such as artificial intelligence, computer vision, and Internet of Things communications, face recognition technology has been widely used in real life, such as smart home appliances, smart retail, and smart monitoring. However, in some application scenarios, due to the limitation of storage space and personal privacy protection, some face recognition systems only include one or a small number of frontal standard images of each person (that is, those that are not disturbed by external factors such as illumination, expression, and occlusion). Frontal ima...

AI Technical Summary

Problems solved by technology

Although this type of method plays a certain role in single-sample face recognition, there are still two fatal flaws: (1) The virtual sample generated by synthesis is highly correlated with the standard sample, so it cannot be used as an independent sample. Intra-class change information is not representative

(2) When the face image is divided into blocks, it is usually assumed that the block image of the test sample and the block image of the training sample at the same position have similar face structural features. However, in practical applications, due to changes in face posture or accessories Due to the influence of occlusion, there may be a big difference between the block image of the test sample and the training sample at the same position, which leads to the above assumptions not being true, and the single-sample face recognition effect is not good

However, in practical applications, it is a daunting task to collect enough generic samples that satisfy various variations

[0007] (2) The atoms in the above dictionary are all represented by the original image, which leads to a large amount of pixel redundant information in the image-based dictionary, lack of consistency between atoms of the same type, and lack of discrimination between atoms of different types; at the same time, the dictionary Atoms are represented by converting two-dimensional images into one-dimensional column vectors, which also causes the dimension of dictionary atoms to be much larger than the number of atoms, which is prone to the "small sample" problem and cannot guarantee the optimal sparse solution in the solution space

Although methods such as SVDL and RADL treat occlusion information as sparse reconstruction errors and can overcome the above problems, such algorithms have high computational complexity and lack operability in practical applications.

Images