Improvement of Patch Selection in Exemplar-based Image Inpainting
Qian Fan, Lifeng Zhang · 2015
In the existing exemplar based image inpainting algorithms, the most similar match patches are used to inpaint the destroyed region, and they are searched in the whole source region in a fixed size. However, sometimes it would decrease the connectivity of structure and clearness of texture while increases the time complexity of this algorithm. To solve these problems, firstly we proposed an adaptive sample algorithm based on patch sparsity, it calculates the patch sparsity which divided the patches’ location into three types (smooth type, transition type and edge type). Then the size of the sample patch can be adaptively changed according to the type. Secondly it proposed a candidate patch system to improve the patch matching rate. From the result, we can see that the proposed method can match more significant patches than the traditional method, and it can give a better texture inpainting effect, especially when processing the complex and regular textures in the image which has a large destroyed region.