Damaged region filling by improved criminisi image inpainting algorithm for thangka
- 365 Downloads
In order to solve the problems of the criminisi algorithm in inpainting thangka image, such as the mistake matching phenomenon, image structure information inconsistent and the inaccurate matching standards, the new image inpainting algorithm based on thangka image structure information is proposed in this paper. The following three steps are the keys of this method. (1) The correlation of repaired block and its neighborhood block is introduced and the priority of formula is improved; (2) The exemplar-based size selection is improved, the adaptive patch size is automatically adjusted according to the exemplar-based information changes; (3) In order to solve mistake matching problem, the structure information of thangka image and color of Euclidean distance are combined as the new matching criterion. The experimental results show that the mistake matching phenomenon by the proposed method for thangka image is significantly reduced, the structure of thangka image is more fluent and smooth than them in comparative literature.
KeywordsThangka Image inpainting Priority function Similarity function
This work was supported by Natural Science Foundation of China (Grant: 61762082), Tibet Program for the Young Teacher in University (Grant: QCZ2016-28), Foundation of Xizang Minzu Universiy (Grant: 16MYQP06).
- 1.Ti, Wang, Wang, W.: Thangka domain ontology reasoning based on Jena. J. Jilin Univ. 46(6), 7–12 (2016)Google Scholar
- 2.Imatiyaz, M., Kumar, A., Sreenivasulu, G.: Inpainting an image based on enhanced resolution. J. Comput. Technol. Appl. 6(1), 23–26 (2015)Google Scholar
- 12.Zun, L.I., Jin, W.U., Jing, L.I.U., et al.: The application of mathematical morphology in the criminisi algorithm of image inpainting. Infrared Technol. 37(7), 574–578 (2015)Google Scholar
- 15.Weilan, W., Yanjun, J.: Damaged region filling and evaluation by symmetrical exemplar-based image inpainting for Thangka. EURASIP J. Image Video Process. 38, 1–38 (2017)Google Scholar