Investigation of Optimal Image Inpainting Techniques for Image Reconstruction and Image Restoration Applications
Main Article Content
Abstract
People in today's society take a lot of pictures with their smartphones and also make an effort to keep their old photographs safe, but with time, those photographs deteriorate. Image inpainting is the art of reconstructing damaged or missing parts of an image. Repairing scratches in photographs or film negatives, or adding or removing elements like stamped dates or "red-eye," are all possible through inpainting. In order to restore the image many techniques have been developed, significant techniques include exemplar based inpainting, coherent based inpainting and method for correction of non-uniform illumination. The four main applications of these image inpainting techniques are scratch removal, text removal, object removal and image restoration. However, all the four image inpainting applications cannot be implemented using a single technique. According to the literature, there has been relatively less work done in the field of image inpainting applications. Investigation has been carried out to find the suitability of these three techniques for the four above mentioned image inpainting applications based on two performance metrics.
Article Details
References
“Image sequence restoration in the presence of pathological motion and severe artifacts,” presented at the IEEE ICASSP, Orlando, FL, USA, May 2002
S. Masnou and J.-M. Morel, “Level-lines based disocclusion,” presented at the IEEE Int. Conf. Image Processing, Chicago, IL, 1998.
C. Ballester et al., “Filling-in by joint interpolation of vector fields and gray levels,” IEEE Trans. Image Process., vol. 10, no. 8, pp. 1200–1211, Aug. 2001
M. Bertalmio, A. Bertozzi, and G. Sapiro, “Navier-stokes, fluid-dynamics and image and video inpainting,” presented at the IEEE CVPR, 2001.
T. Chan and J. Shen, “Mathematical models for local nontexture inpainting,” SIAM J. Appl. Math., vol. 62, no. 3, pp. 1019–1043, 2001
T. Chan, S. H. Kang, and J. Shen, “Euler’s elastica and curvature based inpainting,” SIAM J. Appl. Math., vol. 63, no. 2, pp. 564–592, 2002.
M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Trans. Image Process., vol. 12, no. 8, pp. 882–889, Aug. 2003.
S. Rane, M. Bertalmio, and G. Sapiro, “Structure and texture filling-in of missing image blocks for wireless transmission and compression applications,” IEEE Trans. Image Process., vol. 12, no. 3, pp. 296–303, Mar. 2002.
H. Knutsson and C.-F. Westin, “Normalized and differential convolution: Methods for interpolation and filtering of incomplete and uncertain data,” presented at the IEEE CVPR, New York, 1993.
A. A. Efros and T. K. Leung, “Texture synthesis by nonparametric sampling,” presented at the ICCV, 1999.
A. Criminisi, P. Pérez, and K. Toyama, “Object removal by exemplarbased inpainting,” presented at the IEEE CVPR, 2003.
J. Jia and C.-K. Tang, “Image repairing: Robust image synthesis by adaptive ND tensor voting,” presented at the IEEE CVPR, 2003.
A. N. Hirani and T. Totsuka, “Combining frequency and spatial domain information for fast interactive image noise removal,” in Proc. ACM SIGGRAPH, 1996, pp. 269–276.
F. D. Beulah David and Dorai Rangaswamy “Image Completion by Spatial-Contextual Correlation Framework Using Automatic and Semi-Automatic Selection of Hole Region” Ictact Journal On Image and Video Processing, August 2015, Volume: 06, Issue: 01
Xiaowei Shao,Zhengkai Liu,Li Houqiang “An Image Inpainting approach Based on Poisson equation” Document Image Analysis for Libraries, 2006. DIAL '06. Second International Conference, April 2006.
Qing Zhang and Jiajun Lin “Exemplar-Based Image Inpainting Using Color Distribution Analysis” Journal of Information Science and Engineering 28, 641-654 (2012).
K. Sangeetha, Dr.P. Sengottuvelan and E.Balamurugan “Extended Wavelet Transform Based Image Inpainting Algorithm For Natural Scene Image Completion” Computer Science & Information Technology ( CS & IT ) .