Advertisement

Tampered Image Reconstruction with Global Scene Adaptive In-Painting

  • Ravi Subban
  • Muthukumar Subramanian
  • Pasupathi Perumalsamy
  • R. Seejamol
  • S. Gayathri Devi
  • S. Selvakumar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 264)

Abstract

The objective of in-painting is to reconstruct the mislaid region of an image. This paper presents a new in-painting algorithm from the goodwill of Exemplar-based Greedy algorithms, which consist of two phases: making a decision of filling-in order and selection of good exemplars for the damaged regions. The proposed method overcomes these tribulations with the protection of edges, textures and also with lesser propagation error. This scheme upgrades the filling-in order that is based on the combination of priority terms, to encourage the early synthesis of linear structures. The subsequent contribution helps sinking the error propagation to an improved detection of outliers from the candidate patches. The proposed methodology is well suited in terms of both natural and artificial images with plausible output. This scheme dramatically outperforms earlier works in terms of both perceptual quality and computational efficiency.

Keywords

Curvature Driven Delusion Exemplar based Approach Texture Synthesis Structure Synthesis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mumford, Shah, J.: Optimal approximations by piecewise smooth functions and associated variation problems. Comm. Pure Appl. Math. 42(5), 577–685 (1989) Google Scholar
  2. 2.
    Chen, S.E., Williams, L.: View interpolation for image synthesis. Computer Graphics, SIGGRAPH 27, 279–288 (1993) Google Scholar
  3. 3.
    Efors, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: ICCV (2), pp. 1033–1038 (1999) Google Scholar
  4. 4.
    Levoy, W.: Fast Texture Synthesis using Tree-structured Vector Quantization. In: Proceedings of SIGGRAPH (2000) Google Scholar
  5. 5.
    Xu, Y., Guo, G., Shum, H.Y.: Chaos mosaic: Fast and memory efficient texture synthesis. Tech. Rep., Microsoft Research (April 2000) Google Scholar
  6. 6.
    Bertalmio, et al.: Image in-painting. In: Siggraph, Computer Graphics Proceedings, pp. 417–424. ACM Press/ACM SIGGRAPH (2000) Google Scholar
  7. 7.
    Chan, T.F., Shen, J.: Non Texture inpainting by Curvature-Driven Diffusions (CDD). Jounal of Vis. Comm. Image Rep. 4(12), 436–449 (2001) Google Scholar
  8. 8.
    Tsai, et al.: Curve evolution implementation of the Mumford Shah functional for image segmentation, denoising, interpolation and imagination. IEEE Trans. Image Process. 10(8), 1169–1186 (2001) Google Scholar
  9. 9.
    Esedoglu, S., Shen, J.: Digital inpainting based on the Mumford-Shah-Euler image model. European Journal of Applied Mathematics 13(4), 353–370 (2002) Google Scholar
  10. 10.
    Masnou, S.: Disocclusion: A variational approach using level lines. IEEE Transactions on Image Processing 11, 68–76 (2002) Google Scholar
  11. 11.
    Bertalmio, M., Vese, L., Sapiro, G., Osher, S.: Simultaneous Structure and texture image inpainting. In: Proc. Conf. Comp. Vision Pattern Rec. Madison, WI (2003) Google Scholar
  12. 12.
    Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar based image in-painting. IEEE Trans. on Image Processing 13, 1200–1212 (2004) Google Scholar
  13. 13.
    Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, pp. 860–867 (2005) Google Scholar
  14. 14.
    Wu, J., et al.: Object Removal By Cross Isophotes Exemplar-based In-painting. In: Proceedings of the 18th International Conference on Pattern Recognition, ACM Digital Library Proceeding, ICPR 2006, vol. 3, pp. 810–813 (2006) Google Scholar
  15. 15.
    Roth, S., Black, M.J.: Steerable random fields. In: Proc. IEEE Com-puter Society Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2007) Google Scholar
  16. 16.
    Hong-Bin, Z., Jia-Wen, W.: Image Inpainting by Integrating Structure and Texture Features. Journal of Beijing University of Technology 33(8), 864–869 (2007) Google Scholar
  17. 17.
    Liu, D., et al.: Image Compression With Edge-Based Inpainting. IEEE Transactions on Circuits And Systems For Video Technology 17(10), 1273 (2007) Google Scholar
  18. 18.
    Li, X., Zheng, Y.: Patch based video processing: a variation Bayesian approach. IEEE Transaction on circuits and Systems for Video Technology 19(10), 2476–2491 (2007) Google Scholar
  19. 19.
    Zhou, Zheng.: Gradient based image completion by solving the Poisson equation. Computers & Graphic Science Direct 31(1), 119–126 (2007) Google Scholar
  20. 20.
    Wong, A., Orchard, J.J.: A nonlocal-means approach to exemplar based inpainting. In: IEEE Int. Conf. Image Processing (2008) Google Scholar
  21. 21.
    Shen, B., Hu, W., Zhang, Y., et al.: Image inpainting via sparse representation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, pp. 697–700 (2009) Google Scholar
  22. 22.
    Xu, J., et al.: An Image Inpainting Technique Based on 8-Neighborhood Fast Sweeping Method. In: Published in Proceeding CMC 2009 Proceedings of the WRI International Conference on Communications and Mobile Computing, vol. 3, pp. 626–630. IEEE Computer Society, Washington, DC (2009) Google Scholar
  23. 23.
    Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: Patch match: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24:1–24:11 (2009) Google Scholar
  24. 24.
    Muthukumar, S., Krishnan, N., Pasupathi, P., Deepa, S.: Analysis of Image Inpainting Techniques with Exemplar, Poisson, Successive Elimination and 8 Pixel Neighborhood Methods. International Journal of Computer Applications 9(11), 15–18 (2010) Google Scholar
  25. 25.
    Bugeau, Bertalmio, M., Caselles, V., Sapiro, G.: A comprehensive framework for image inpainting. IEEE Trans. Image Process. 19(10), 2634–2645 (2010) Google Scholar
  26. 26.
    Lu, Z., et al.: A Novel Hybrid Image Inpainting Model. presented at the IEEE International Conference on Genetic and Evolutionary Computing (2010) Google Scholar
  27. 27.
    Xu, Z., Sun, J.: Image inpainting by patch propagation using patch sparsity. IEEE Trans. Image Process. 19(5), 1153–1165 (2010) Google Scholar
  28. 28.
    Zhong, Z., Wang: Image inpainting-based edge enhancement using the eikonal equation (2011) 978-1-4577-0539-7/ IEEE Google Scholar
  29. 29.
    Jian-Bin, Y.: Image in-painting using complex 2-D dual-tree wavelet transform. Appl. Math. J. Chinese University 26(1), 70–76 (2011) Google Scholar
  30. 30.
    Zontak, M., Irani, M.: Interfinal statistics of a single natural image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011) Google Scholar
  31. 31.
    Li, S., Zhao, M.: Image in-painting with salient structure completion and Texture propagation, 0167-8655/ Elsevier, pattern Recognition (2011) Google Scholar
  32. 32.
    Turkan, M.: Novel texture synthesis methods and their application to image prediction and image inpainting. Ph.D. thesis, Univ. Rennes 1 (2011) Google Scholar
  33. 33.
    Mart Inez-Noriega, R.: Exemplar-Based Image In-painting: Fast Priority and Coherent Nearest Neighbor Search. In: IEEE International Workshop on Machine Learning for Signal Processing, pp. 23–26 (2012) Google Scholar
  34. 34.
    Mahajan, K.S., Vaidya, M.B.: Image in Painting Techniques: A survey. IOSR Journal of Computer Engineering (IOSRJCE) 5(4), 45–49 (2012) ISSN: 2278 - 0661, ISBN: 2278 – 8727 Google Scholar
  35. 35.
    Subban, R., Pasupathi, P., Muthukumar, S.: Image Restoration Based on Scene Adaptive Patch In-painting for Tampered Natural Scenes. Recent Advances in Intelligent Informatics, Advances in Intelligent Systems and Computing 235 (2013), doi:10.1007/978-3-319-01778-5-7, @Springer International Publishing SwitzerlandGoogle Scholar
  36. 36.
    Baek-Sop Kim, S., Park, J.: Exemplar Based Image Inpainting on a Projection Framework. International Journal of Software Engineering and Its Applications 7(3) (May 2013) Google Scholar
  37. 37.
    Subban, R., Pasupathi, P., Muthukumar, S., Krishnan, N.: Image Inpainting Techniques – A Survey and Analysis. In: International Conference on IIT, 978-1- 4673-6203-0© Conference on United Arab Emirates University, Dubai IEEE (2013) Google Scholar
  38. 38.
    Das, S., Reeba, R.: IJSER. Robust Exemplar based Object Removal in Video 1(2) (2013), ISSN 2347-3878 Google Scholar
  39. 39.
    Sangeetha, K., Sengottuvelan, P., Balamurugan, E.: Performance analysis of exemplar based image inpainting algorithms for natural scene image completion. In: International Conference on Intelligent Systems and Control (ISCO), pp. 276–279. IEEE (2013) Google Scholar
  40. 40.
    Doria, D.: A Greedy Patch-based Image Inpainting Framework. Posted in Scientific Visualization, ITK Google Scholar
  41. 41.
    Ashikhmin, M.: Synthesizing natural textures. In: ACM Symposium on Interactive 3D Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ravi Subban
    • 1
  • Muthukumar Subramanian
    • 2
  • Pasupathi Perumalsamy
    • 3
  • R. Seejamol
    • 3
  • S. Gayathri Devi
    • 3
  • S. Selvakumar
    • 3
  1. 1.Dept of CSEPondicherry UniversityPondicherryIndia
  2. 2.Dept of CSENITPondicherryIndia
  3. 3.CITEMS UniversityTirunelveliIndia

Personalised recommendations