An Improved Criminisi’s Image Inpainting Algorithm for Priority and Matching Criteria

There are many applications of image inpainting. Criminisi algorithm is a classical sample-based inpainting method in image inpainting technology. Aiming at the distortion caused by unreasonable priority calculation and similarity matching criteria calculation in the Criminisi algorithm, in this paper, an improved Criminisi algorithm for priority and similarity matching criteria are presented. Experiments show that the improved algorithm has better performance.

[1]  Fulong Wang,et al.  Improved Criminisi Algorithm Based on a New Priority Function with the Gray Entropy , 2013, 2013 Ninth International Conference on Computational Intelligence and Security.

[2]  Tony F. Chan,et al.  Non-texture inpainting by curvature-driven diffusions (CDD) , 2001 .

[3]  Anupam,et al.  Fast and Enhanced Algorithm for Exemplar Based Image Inpainting , 2010, 2010 Fourth Pacific-Rim Symposium on Image and Video Technology.

[4]  Ling Xiong,et al.  Criminisi-Based Sparse Representation for Image Inpainting , 2017, 2017 IEEE Third International Conference on Multimedia Big Data (BigMM).

[5]  Xingming Sun,et al.  A robust forgery detection algorithm for object removal by exemplar-based image inpainting , 2017, Multimedia Tools and Applications.

[6]  Tony F. Chan,et al.  Nontexture Inpainting by Curvature-Driven Diffusions , 2001, J. Vis. Commun. Image Represent..

[7]  Tony F. Chan,et al.  Mathematical Models for Local Nontexture Inpaintings , 2002, SIAM J. Appl. Math..

[8]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.