Multi-exemplar synthesis image inpainting algorithm with regulatory factor

This paper proposes a novel multi-exemplar synthesis image inpainting algorithm with regulatory factor. The Criminisi image inpainting algorithm often experiences problems of mismatch, quality of information diffusion, and high cumulative error. The regulatory factor β is employed in this paper to adjust the priority of the padding edge, which makes the proposed algorithm more sensitive to the details of the image textures and improves the boundary repairing effect. Combining the gradient information and histogram information to find the best matching block, the multiple exemplars synthesis strategy is introduced to satisfy the vision requirements of image fusion. The experimental results show that the proposed algorithm is able to provide very competitive results in comparison with the Criminisi algorithm. © 2015 ICIC International.