Affine transformation-based frontal face image super-resolution reconstruction method

Abstract

The invention discloses an affine transformation-based frontal face image super-resolution reconstruction method. In the method, a recently popular two-step method is adopted to perform super-resolution reconstruction on images, wherein a first step is used for reconstructing intermediate-low frequency information (a global structure) for testing low-resolution images, namely, firstly blocking all images, establishing mapping relationship between a high-resolution pixel space and a low-resolution pixel space at each block position respectively and performing the super-resolution reconstruction on the tested low-resolution images through an obtained mapping matrix to obtain a first-step high-resolution reconstructed image block of each block position; and a second step is used for reconstructing high-frequency information (detailed information), namely, performing error compensation on the reconstructed image blocks obtained in the first step according to LLE to obtain a residual image block at each block position, adding the high-resolution reconstructed image block at each block position and the corresponding residual image block to obtain a super-resolution reconstructed image block and finally synthesizing all the super-resolution reconstructed image blocks into a complete image which is a super-resolution reconstruction result corresponding to the tested images.

Description

field of invention [0001] The invention relates to a face image reconstruction method, in particular to a frontal face image super-resolution reconstruction method based on affine transformation. Background technique [0002] In most digital image applications, it is desirable to obtain high-resolution images. The super-resolution reconstruction of low-resolution frontal face images can obtain high-pixel frontal face images with a lot of detailed information, which is convenient for applications in many fields such as surveillance. [0003] Precisely due to the widespread availability of high-resolution images, various methods have emerged in recent years to improve the quality of the resulting images. Early super-resolution reconstruction methods include bicubic interpolation, convex set projection and so on. In recent years, super-resolution reconstruction methods based on learning-based neighborhood reconstruction have compared manifolds and achieved good results. Howe...

AI Technical Summary

Problems solved by technology

However, neighborhood reconstruction requires that the corresponding high- and low-resolution image features have the same manifold, so if the image feature space is not properly searched, the super-resolution reconstruction results will be noisy and the image will be slightly distorted.

Images