Modification of Exemplar-Based Inpainting Algorithm for Mobile Devices With of Patch Offsets
Keywords:
Image inpainting, Image completion, Exemplar-based algorithmAbstract
Inpainting (completion) of digital images is the process of filling in an unknown region with information from the known region of the image. Due to rise of mobile technologies, there is demand on usage of inpainting algorithms on mobile devices for applications such as object removal, image restoration, etc. Exemplar-based inpainting is one of the most popular and efficient inpainting algorithms, but, however, it is slow enough for mobile implementation. The intention of this paper is to develop a high performance inpainting algorithm applicable for mobile devices. We introduce a modification of the algorithm using the statistics of similar patch offsets. This approach reduces the computation time at about 10-30 times, which makes the algorithm work interactive even on mobile devices. The paper includes those experiment results and comparison of the developed algorithm with the exemplar-based inpainting algorithm and showed the advantages of our method on various images.
References
N. Komodakis and G. Tziritas, “Image completion using efficient belief propagation via priority scheduling and dynamic pruning,” IEEE Trans. Image Process. , vol. 16, no. 11, pp. 2649–2661, 2007.
M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester. “Image inpainting”, Proceedings SIGGRAPH 2000, Computer Graphics Proceedings, pp. 417—424, 2000.
A. Criminisi, P. Perez and K. Toyama, “Region filling and object removal by exemplar-based image inpainting,” IEEE Transactions on Image Processing, vol. 13, no. 9, pp. 1200–1212, 2004.
C. Barnes, E. Shechtman, A. Finkelstein and D. B. Goldman, “PatchMatch: A randomized correspondence algorithm for structural image editing,” in Proc. Annu. Conf. Comput. Graph. Interact. Techn., pp. 1–8, 2009
K. He and J. Sun, “Computing nearest-neighbor fields via propagation-assisted KDtrees,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 111–118, 2012
K. He and J. Sun, “Image completion approaches using the statistics of similar patches”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 12, pp. 2423-2435, 2014
G.Karapetyan, H.Sarukhanyan and S. Agaian “Robust digital image inpainting algorithm in the wireless environment”, SPIE Proceedings, vol. 9120, 8 pages, 2014 doi:10.1117/12.2049942
G.Karapetyan and H.Sarukhanyan. “Automatic detection and concealment of specular reflections for endoscopic images” Ninth International Conference Computer Science and Information Technologies, Revised Selected Papers, IEEE Explore, 8 pages, 2013, 10.1109/CSITechnol.2013.6710353
G.Karapetyan and H.Sarukhanyan. “Automatic detection and concealment of specular reflections for endoscopic images”, Proceedings of International Conference Computer Science and Information Technologies, pp.197-200, 2013.
G.Karapetyan and H.Sarukhanyan. “Concealment of targeted regions in digital images on mobile devices”, Transactions of IIAP NAS RA, Mathematical Problems of Computer Science, vol. 40, pp. 68--75, 2013.
G.Karapetyan, “Modification of FSE method based on coefficients of homogeneity”, Transactions of IIAP NAS RA,Mathematical Problems of Computer Science , vol. 35, pp. 109-115, 2011.
G.Karapetyan and H.Sarukhanyan, “On a modification of the frequency selective extrapolation method“, Information Models and Analyses, vol.2, pp.139-145, 2012.
[Online]. Available: http://opencv.org/
[Online]. Available: http://developer.android.com/intl/ru/tools/sdk/ndk/index.html
[Online]. Available:http://www.ni.com/white-paper/13306/en/
Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
