Face image super-resolution method based on local and sparse non-local regularities

Abstract

The invention discloses a face image super-resolution method based on local and sparse non-local regularities. The face image super-resolution method comprises the following steps of 1, obtaining image blocks of all pixel positions of a test image and a training sample image; 2, using a local PCA dictionary learning method, using a K-means clustering algorithm to divide and cluster the image blocks of the training sample image blocks, and learning a local PCA dictionary by each cluster; 3, for a low-quality image block, solving an optimal representation coefficient vector by applying a local constraint and sparse non-local dual-core norm regularization algorithm; 4, synthesizing a high-resolution image block on the high-resolution dictionary by using the optimal representation coefficientvector, updating a non-local coding coefficient, and putting the updated coefficient and the high-resolution image block into the step 3 for next iteration; A high-resolution image block is obtained through multiple times of iterative updating; And step 5, outputting a high-resolution image. The method has the advantage of improving the image quality.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a face image super-resolution method based on local and sparse non-local regularization. Background technique [0002] With the development of information technology, people's requirements for face image processing are increasing. For example, in intelligent monitoring systems, high-quality images with rich details are very important. They can effectively improve system performance and reduce the low It is also crucial that resolution images become high-resolution images. This method of restoring high-resolution images from low-resolution images is face super-resolution technology. [0003] Existing face image super-resolution methods are mainly divided into two categories, one is reconstruction-based techniques, and the other is learning-based techniques. Compared with reconstruction-based techniques, learning-based techniques can also achieve more stable and better p...

AI Technical Summary

Problems solved by technology

[0006] Some previous methods assume that low-resolution image blocks and high-resolution image blocks have the same topology, so the encoding coefficients generated by low-resolution test image blocks are directly used to synthesize high-resolution image blocks, but this ignores high-resolution image blocks. rate image block topology, which may distort the coefficients and affect image quality

Images