IIAE CONFERENCE SYSTEM, The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)

Font Size: 
Image Painting Based FMM Algorithm Using Gradient Matrix
Qian Fan, Xuelong Hu, Lifeng Zhang

Last modified: 2013-10-01


In this paper, we propose an improved image inpainting method based on FMM algorithm. The traditional approach gives a fast processing speed but it cannot contribute an optimal edge result. Using gradient matrix to detect the texture direction, the significant pixels for the inpainting process are selected. Furthermore, this procedure also reduced the noise pixels’ influence. Therefore, it can yield a better edge effect for inpainting procedure than the traditional approach.


Image inpainting, FMM algorithm, Gradient matrix


[1] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester,“Imageinpainting,”in Proc. SIGGRAPH, 2000, pp. 417–424.

[2]M. Bertalmio, A. L. Bertozzi, and G. Sapiro, “Navier–Strokes,fluid dynamics, and image and video inpainting,” in Proc. IEEEComputer Society Conf. Computer Vision and Pattern Recognition,2001, pp.417–424.

[3] T. Chan and J. Shen, “Localinpainting models andtvinpainting,” SIAM J. Appl. Math., vol. 62, no. 3, pp. 1019–1043,2001.

[4] T. Chan and J. Shen, “Non-textureinpainting bycurvature-driven diffusions,” J. Vis. Commun. Image Represent.,vol. 4, no. 12, pp. 436–449, 2001.

[5] C. Bertalmio, M. Bertalmio, V. Caselles, G. Sapiro, and J.Verdera, “Filling-in by joint interpolation of vector fields and graylevels,” IEEE Trans. Image Process., vol. 10, pp. 1200–1211, 2001.

[6] A. Levin, A. Zomet, and Y. Weiss, “Learning how to inpaintfrom global image statistics,” in Proc. Int. Conf. Comp. Vision, pp.305–313.

[7] S. Roth and M. J. Black, “Fields of experts: A framework forlearning image priors,” in Proc. IEEE Computer Society Conf.Computer Vision and Pattern Recognition, 2005, pp. 860–867.

[8] S. Roth and M. J. Black, “Steerable random fields,” in Proc.IEEE Computer Society Conf. Computer Vision and PatternRecognition, 2007, pp. 1–8.

[9] A. Efros and T. Leung, “Texture synthesis by non-parametricsampling,” in Proc. Int. Conf. Comp. Vision, 1999, pp. 1033–1038.

[10] M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneousstructure and texture imageinpainting,” IEEE Trans. ImageProcess., vol. 12, pp. 882–889, 2003.

[11] A. Criminisi, P. Perez, and K. Toyama, “Object removal byexemplar-based imageinpainting,” in Proc. Int. Conf. Comp. Vision,2003, pp. 721–728.

[12] J.Wu and Q. Ruan, “Object removal by cross isophotesexamplar-based imageinpainting,” in Proc. Int. Conf. PatternRecognition, 2006, pp. 810–813.

[13] A. Wong and J. Orchard, “A nonlocal-means approach toexamplarbasedinpainting,” presented at the IEEE Int. Conf. ImageProcessing, 2008.

[14] Telea A. An image inpainting technique based on the fastmarching method. Journal of Graphics Tools,2004,9(1) :23-34.

[15] yan-xi Yang, Xiao-yan Juan, An improved image inpaintingalgorithm based on fast marching method. Journal of Xi'anUniversity of Technology,2009,25(2:129-134)

Full Text: PDF