A method for image inpainting with sample block sparsity combined with direction factor

Abstract

Disclosed is a swatch sparsity image inpainting method with directional factors combined. The swatch sparsity image inpainting method mainly comprises the steps of conducing preprocessing on an image to be inpainted by the utilization of an existing image inpainting algorithm, extracting directional factors in four directions from the preprocessed image through non-subsampled contourlet transform, determining a new structural sparseness function and a new matching criterion according to the color-directional factor weighting distance, determining a filling-in order by means of the structure sparseness function and searching for a plurality of matching blocks according to the new matching criterion, establishing a constraint equation with color space local sequential consistency and directional factor local sequential consistency, optimizing and solving the constraint equation to obtain sparse representation information of the matching blocks, conducting filling, and updating filled-in regions until damaged areas are completely filled in. By means of the swatch sparsity image inpainting method, the consistency of the structure part, the clearness of the texture part and the sequential consistency of neighborhood information can be effectively kept, and the swatch sparsity image inpainting method is particularly applicable to inpainting of real pictures or composite images with complex textures and complex structural characteristics.

Description

technical field [0001] The invention relates to an image restoration method based on sample blocks, in particular to an image restoration method based on the sparseness of sample blocks. Background technique: [0002] Digital image restoration is a technology that repairs the damaged area according to certain rules based on the known information in the damaged image. Its purpose is to make the observer unable to detect that the image has been damaged or has been repaired. With the development of digital image processing technology, digital image restoration technology has become a research hotspot in computer graphics and computer vision. It has great application value in cultural relics protection, film and television special effects production, image lossy compression, specific object removal, etc. . Currently, digital image inpainting techniques are mainly divided into two categories: diffusion-based image inpainting algorithms and sample block-based image inpainting alg...

AI Technical Summary

Problems solved by technology

The above three methods only use color information to measure the similarity between sample blocks, which not only makes the found matching blocks unreasonable, but also has a negative impact on the construction of the structure sparsity function

Document 3 still adopts the priority calculation method in Document 1, the filling order is not stable enough, and the continuity of the structural part cannot be well maintained

Although Document 2 and Document 4 use the structural sparsity function to determine the filling order, the structural sparsity function is determined by the similarity function and the proportion of known blocks in the neighborhood of the block to be filled. Not only is the similarity function unreasonable, but also When there are few known blocks in the neighborhood of the structure block, the structure sparsity value is small, and the structure block cannot be filled preferentially

Moreover, the above three methods only establish neighborhood consistency constraints in the color space, which cannot well maintain the clarity of the texture area and structure area of ​​the repaired image, and there is a certain blur effect.

Images