Super-resolution reconstruction method of mine image based on online multi-dictionary learning

Abstract

Aiming at problem that dictionary learning method was poorly effective in reconstruction of mine image with noise and complex environment, a super-resolution reconstruction method of mine image based on online multi-dictionary learning was proposed. The method uses K-means clustering algorithm to divide image training set into multiple kinds of images, and trains multiple sets of high-resolution dictionaries and low-resolution dictionaries for different kinds of images, so as to improve feature representation ability of the dictionaries for complex environmental images. According to non-local self-similarity of image, non-local constraint is introduced to further constrain solution space of sparse coefficient, and online dictionary learning is used to optimize the dictionaries in the multi-dictionary learning stage, so as to improve accuracy of sparse coefficient solution and anti-noise interference ability of image reconstruction process. The experimental results show that the method can effectively improve quality of reconstructed image, suppress image blocking effect and edge jagged effect caused by noise, enhance image details, and achieve better visual effect.

Keywords

• mine image
• super-resolution reconstruction
• online dictionary learning
• multi-dictionary learning
• non-local self-similarity