Summary

Proceedings of the 2012 International Symposium on Nonlinear Theory and its Applications

2012

Session Number:A2L-A

Session:

Number:90

Interactive Segmentation for Color Image based on Visual Saliency

Daiki Gion,  Hironori Takimoto,  Yasue Mitsukura,  Mitsuyoshi Kishihara,  Kensuke Okubo,  

pp.90-93

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.1.90

PDF download (558.1KB)

Summary:
The problem of efficient, interactive image segmentation in still image is of great practical importance in image editing. Recently, an approach based on optimization by graph-cut has been developed. However, interactive image segmentation approach which is intuitive and efficient to users is required. In this paper, we proposed novel interactive image segmentation method based on visual saliency. In this method, a user provides only some foreground pixels as seeds. Image segmentation is performed by optimizing proposed graph by using the graph-cut algorithm. In addition, in order to achieve an efficient segmentation, concept of neighborhood is extended to long-range neighborhood.

References:

[1] V. S. Lempitsky, P. Kohli, C. Rother, and T. Sharp, “Image segmentation with a bounding box prior.,” Proc. of ICCV 2009, pp. 277-284, 2009.

[2] Y. Boykov and M. Jolly, “Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images,” Proc. of ICCV 2001, vol. I, pp. 105-112, 2001.

[3] V. Q. Pham, K. Takahashi, and T. Naemura: “Bounding-box based Segmentation with Single Min-Cut using Distant Pixel Similarity”, Proc. of ICPR 2010, pp. 4420-4423, Turkey, 2010.

[4] C. Rother, V. Klomogorox, and A. Blake: “Grabcut: interactive foreground extraction using iterated graph cuts,” Proc. of SIGGRAPH, Vol. 23, pp. 309-314, 2004.

[5] C. Stauffer and W.E.L Grimson: “Adaptive Background Mixture Models for Real-time Tracking”, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp.246-252, 1999.

[6] K. Inoue, K. Hara, K. Urahama: “Saliency Map Based on Color Histograms of Inside and Outside of Clipped Rectangular Region”, The journal of the Institute of Image Information and Television Engineers, vol. 65, no. 7, pp.996-999, 2011. (in Japanese)

[7] F. Meyer: “Color Image Segmentation,” Proc. International Conference on Image Processing and its Aplications, pp.303-306, 1992.

[8] Y. Boykov and V. Kolmogorov: “An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.26, no.9, pp.1124-1137, 2004.