Single-sample face recognition method based on sparse representation of hybrid extension block dictionary

Abstract

The invention discloses a single-sample face recognition method based on sparse representation of a hybrid extension block dictionary. The method comprises the following steps: (S1) constructing a general data set X of a non-target object; (S2): constructing a target object standard sample set N; (S3): constructing a test sample set Y; (S4) constructing a shielding block dictionary of a non-target object and an intra-class difference block dictionary; and (S5) performing linear sparse representation on B block images of a to-be-detected sample y of the target object by adopting a weighted block sparse representation classifier in the SRC model according to the mixed complete extension block dictionary obtained in the above step so as to perform shielding face recognition on the to-be-detected sample. According to the method, firstly, the face image is partitioned, then, the basic block dictionary of the target object, the shielding block dictionary of the non-target object and the intra-class difference block dictionary are constructed by adopting the KDA algorithm, and finally, the to-be-detected sample is accurately predicted by adopting the weighted block sparse representation classifier, so that the accuracy of single-sample face recognition is effectively improved.

Description

technical field [0001] The invention relates to the technical field of single-sample face recognition with only one or a small number of standard samples for the recognition object in human-computer interaction, in particular to a single-sample face recognition method based on sparse representation of a mixed expansion block dictionary. Background technique [0002] In recent years, due to the rapid development of artificial intelligence, computer vision, Internet of Things communication and other technologies, 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 the protection of personal privacy, some face recognition systems only contain one or a small number of standard frontal images of each person (that is, images that are not disturbed by external factors such as illumination, expression, and occlusion). Fronta...

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