Effective inpainting method for natural textures with gradually changed illumination
- 57 Downloads
Natural textures with gradually changed illumination bring great troubles to the field of image inpainting. Using the improved dynamical modeling approach, an energy function model gradually changed from the center to the boundary of data missing region of image is established. On this basis, a gradually changed directional priority function is proposed to ensure the gradual propagation of texture synthesis. In addition, to achieve the feasible propagation of the boundary between different textural regions, the relative test point selection, as well as energy function modeling approach, is also discussed for different cases. Besides, the established energy function models are theoretically evaluated to demonstrate their accuracy in images. Experimental results show the effectiveness of the proposed approach in the natural images with gradually changed illumination.
KeywordsImage inpainting Exemplar-based method Gradually changed illumination Energy function modeling
We would like to thank Mr. Ping-fan Tang for sharing the code of Kansa algorithm. This work was supported in part by the National Natural Science Foundation of China under Grant No. 61271326.
- 1.Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: Proc. IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, Madison, WI (2003). https://doi.org/10.1109/cvpr.2003.1211538
- 3.Xi, X.Y., Wang, F.L., Liu, Y.F.: Improved Criminisi algorithm based on a new Priority Function with the gray entropy. In: 9th International Conference on Computational Intelligence and Security (CIS). IEEE (2013). https://doi.org/10.1109/cis.2013.52
- 5.Nan, A.J., Xi, X.Q.: An improved Criminisi algorithm based on a new priority function and updating confidence. In: 7th International Conference on Biomedical Engineering and Informatics (2014). https://doi.org/10.1109/bmei.2014.7002897
- 9.Chen, X.W., Zhou, B., Guo, Y., Xu, F., Zhao, Q.: Structure guided texture inpainting through multi-scale patches and global optimization for image completion. Sci. China Inf. Sci. 57, 1–16 (2014)Google Scholar
- 15.Fedorov, V., Arias, P., Facciolo, G., Ballester, C.: Affine invariant self-similarity for exemplar-based inpainting. In: Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (2016)Google Scholar
- 17.Xue, S., Dai, Q.H.: Nonlinear Poisson image completion using color manifold. In: Int. Conf. on Image Processing, San Antonio, Texas, USA (2007). https://doi.org/10.1109/icip.2007.4379998
- 19.Fawzi, A., Samulowitz, H., Turaga, D., Frossard, P.: Image inpainting through neural networks hallucinations. In: IEEE Image, Video, and Multidimensional Signal Processing Workshop (2016)Google Scholar