Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning

Abstract

The invention discloses an image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning, mainly aims at solving the problem that the quality of a reconstructed image of the existing method is relatively reduced seriously under a high-magnification factor. The method comprises the following steps of: inputting a training image, filteringthe image to extract characteristics; extracting tectonic characteristics vector sets of small characteristic blocks, and clustering to obtain sample pair sets {(H1, L1), (H2, L2), ..., (HK, LK)} of K to high resolution and low resolution; developing K high-resolution dictionaries Dh1, Dh2, ..., DhK and corresponding low-resolution dictionaries Dl1, Dl2, ..., DlK from the K groups of sample pair sets by means of a KSVD method; encoding low-resolution patterns input in the low-resolution dictionaries Dl1, Dl2, ..., DlK; obtaining an initial reconstruction image by encoding and high-resolution dictionaries Dh1, Dh2, ..., Dh; then implementing local constrained optimization of the initial reconstruction image; and compensating residual errors and implementing global optimization treatment toobtain a final reconstruction image. The image super-resolution reconstruction method based on multitask KSVD dictionary learning has the advantages that the various natural images can be reconstructed, the quality of the reconstructed image can be effectively improved under the condition of a high-magnification factor, and the method can be applied to the recover and identification of human, animal, plant and building and other target objects.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image super-resolution reconstruction method, that is, by learning the relationship between a low-resolution image and a high-resolution image, a single low-resolution image is reconstructed from an input Its corresponding high-resolution images can be used for super-resolution reconstruction of various natural images. Background technique [0002] Super-resolution image reconstruction can be regarded as an inverse problem of reconstructing the corresponding high-resolution image from one or more low-resolution images. In order to solve this problem, some traditional model-based methods are proposed: such as MAP (maximum a-posteriori) method, maximum likelihood estimation method, convex set projection method POCS, etc. However, these traditional methods will produce over-smoothing and jagged effects, and the quality of the reconstructed image will be seriously degraded...

AI Technical Summary

Problems solved by technology

However, these traditional methods will produce over-smoothing and jagged effects, and the quality of the reconstructed image will be severely degraded under high magnification factors.

Therefore, Freeman et al. proposed a learning-based reconstruction method, which mainly learns the relationship between low-resolution images and high-resolution images through Markov stochastic models and prior knowledge. The image is reconstructed to its corresponding high-resolution image, but this method cannot well preserve the boundary information of the high-resolution reconstructed image

Sun et al. have extended this method, m

Images