A novel patch matching algorithm for exemplar-based image inpainting

In the existing exemplar-based image inpainting algorithms, the Sum of Squared Differences (SSD) method is employed to measure the similarities between patches in a fixed size, and then using the most similar one to inpaint the destroyed region. However, sometimes only calculating the SSD difference would produce a discontinuous structure and blur the texture. To solve this problem, we firstly optimize the inpainting priority function and proposed an adaptive patch method to obtain more significant patches. The adaptive patch method changes the size of the patch by computing the patch sparsity. Secondly the proposed method calculates the maximum similarity between patches in different rotation angles so that it obtains the most similar rotation invariant matching patch. From the experimental results, the proposed method can improve the accuracy of the patch selection process compared with the traditional methods, and the proposed method can keep a better global visual appearance, especially for the image which contains more structure contents and the images whose destroyed region has a large width.