Human face image super-resolution recognition method based on fractional order multi-set partial least squares

Abstract

The invention discloses a human face image super-resolution recognition method based on fractional order multi-set partial least squares. The method comprises the following steps of: 1, learning a correlation relationship between views with different resolutions by using a training set in a training stage, reducing dimensions of an image by using PCA (Principal Component Analysis), re-estimating intra-group and inter-group covariance matrixes by using a fractional order thought, calculating an FMPLS projection matrix, and projecting principal component features to a consistent coherent subspace of the FMPLS; step 2, in a test stage, extracting principal component features of a plurality of input low-resolution images, projecting the principal component features to corresponding FMPLS subspaces, and reconstructing high-resolution features of the input low-resolution images through a neighborhood reconstruction strategy; and 3, finally, carrying out face recognition by utilizing a nearest neighbor classifier. According to the method, the fractional order multi-set partial least squares are utilized, mapping of various specific resolutions between face views with different resolutionscan be learned at the same time, and meanwhile, the covariance matrix is estimated again by means of the fractional order thought, so that the influence caused by factors such as insufficient samplenumber and noise is reduced.

Description

technical field [0001] The invention relates to the field of human face super-resolution recognition, in particular to a method for human face image super-resolution recognition based on fractional order multi-set partial least squares. Background technique [0002] In real-world applications, especially in the field of video surveillance, due to factors such as poor lighting conditions and long imaging distances, face images captured by devices are usually low-resolution, which is difficult for traditional face recognition algorithms. Said it was a big problem. In order to solve this problem, many face super-resolution reconstruction methods have been proposed in recent years, aiming to restore the input low-resolution face image to a high-resolution image. [0003] Multivariate analysis methods are often used in super-resolution reconstruction for feature extraction, among which principal component analysis (Principal Component Analysis, PCA) is more popular, and the feat...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the defects of the prior art, provide a face image super-resolution recognition method based on fractional order multi-set partial least squares, and solve the problem that in the prior art, it is impossible to simultaneously learn the correlation between multiple resolution views. relationship and the problem that the covariance matrix may be biased

Images