An improved Criminisi method for image inpainting
Chenzdong Li, Hongyuan Chen, Xiao Han, Xiao Pan, Dongshuai Niu · Journal of Physics Conference Series · 2022
Abstract The Criminisi method is a classical image inpainting method, which has flaw of unreasonable priority calculation. To overcome this flaw, we propose an improved Criminisi method. To improve the accuracy of a repaired block’s priority, we propose a novel method by considering the continuity of structure and color information between the repaired block and its adjacent blocks. When searching the matching block for a repaired block, we compute the similar between two blocks as the sum of squared differences (SSD). Since different blocks within an image may contain different levels of information, we set block to different sizes to determine the best matching block. Experimental results demonstrate the effectiveness of the proposed method.