Image Inpainting Based on Fast Inpainting and Sparse Representation Method

Abstract:

Especially there is a wide interest in handling the outdoor surveillance images in autonomous navigation, remote surveillance, automatic incident detection, vision based driver assistant system and law enforcement services. In each case, there is an underlying object or scene which is wished to be captured, processed, analyzed and interpreted. Live recording and transmission of outdoor surveillance images are often one of a forensic tool but while transmission it may introduce some variations in the pixels and it may visible as missing blocks. Thus it is significant to improve the visual quality of such outdoor surveillance images for efficient analysis and recognition. In this paper, a simple effective inpainting method is proposed by combining fast inpainting and sparse representation method. The proposed method fully considers the complementary between the fast inpainting method and sparse representation inpainting approach. This approach inpaints the small size missing blocks more effectively than the existing inpainting methods. The experimental results on practical images show that the proposed algorithm can achieve a plausible visual performance without discontinuity in boundary and blurring. Keywords:Image Inpainting, Sparse Representation, Fast inpainting

• Periodical: Advanced Materials Research (Volumes 984-985)
• Pages: 1350-1356
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.984-985.1350
• Online since: July 2014
• Authors: C. Ramya*, S. Subha Rani, G. Kayalvizhi
• Keywords: Fast Inpainting, Image Inpainting, Sparse Representation

References

[1] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester. Image inpainting,. In Proc. of ACM Conf. Comp. Graphics (SIGGRAPH), July 2000 pages 417-424.

DOI: 10.1145/344779.344972

[2] M. Oliviera, B. Bowen, R. McKenna, and Y. -S. Chang. Fast digital image inpainting,. In Proc. of Intl. Conf. on Visualization, Imaging and Image Processing(VIIP), 2001. page 261-266.

[3] T. Chan and J. Shen. Mathematical models for local deterministic in-paintings,. Technical Report CAM TR 00-11, UCLA, March 2000, page 1-10.

[4] Coloma Ballester, Marcelo Bertalmio, Vicent Caselles, Guillermo Sapiro, Joan Verdera, Filling in by joint interpolation of vector fields and gray levels, IEEE Transactions on Image Processing, 2001, Vol. 10, No. 8, p.1200–1211.

DOI: 10.1109/83.935036

[5] Zhaoxia Wang, Quan Wang, CS Chang, Ming bai, Zhen Sun, Ting Yang, Image Inpainting Method based on Evolutionary Algorithm, International Journal of Digital Content Technology and its Applications, , 2011, Vol. 5, No. 4, pp.187-193.

[6] Alexei Efros, Thomas Lung, Texture synthesis by non-parametric sampling, In Proceeding of International Conference on Computer Vision, 1999, pp.1033-1038.

[7] A. Criminisi, Patrick Perez, and Kentaro Toyama. Region Filling and object removal by exemplar-based inpainting,. IEEE Transactions on Image Processing, September 2004, 1200-1212.

DOI: 10.1109/tip.2004.833105

[8] Nikos Komodakis, Georgios Tziritas Image completion using efficient belief propagation via priority scheduling and dynamic pruning, IEEE Transactions on Image Processing, 2007, Vol. 16, p.2649–2661.

DOI: 10.1109/tip.2007.906269

[9] Julien Mairal, Michael Elad, Guillermo Sapiro, Sparse representation for color image restoration, IEEE Transactions on Image Processing, 2008, Vol. 17, No. 1, pp.53-69.

DOI: 10.1109/tip.2007.911828

[10] Ming Zhao, Shutao Li, Hybrid Inpainting Algorithm Based on Sparse Representation and Fast Inpainting Method, International Journal of Digital Content Technology and its Applications. July 2011, Vol. 5, pp.239-347.

DOI: 10.4156/jdcta.vol5.issue7.30