Color Image Segmentation Based on Secondary Watershed and GrowCut Algorithm

Abstract:

GrowCut algorithm is not only an interactive algorithm on the basis of cell automata, but also a multi-label algorithm based on seeds point. Aiming at the GrowCut algorithm usually asks users to partition foreground and background manually and mark a lot more initial seeds. This paper presents an automatic object segmentation method which combining secondary watershed and GrowCut algorithm, here in the following paper refers it to as SWGC algorithm. It firstly using the twice used watershed algorithm to partition the input image, the segmented regions are labeled using Mahalanobis distance, and merged according to the image color and space information, thereafter applying the GrowCut algorithm to perform globally optimized segmentation. The main contribution focuses on performing automatic segmentation which consist of obtain the foreground and background region and generate the seed template of GrowCut algorithm automatically. Thus not only leave out the constraints of user interaction operation, but also avoid the subjectivity and uncertainty. The proposed method reduces the runtime significantly as well as improves the segmentation accuracy and robustness of GrowCut algorithm. Experimental results show SWGC algorithm has superior performance compared to the other related methods.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 4032-4037
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.4032
• Online since: July 2014
• Authors: Jian Mei Chen*, Hai Ying Lu
• Keywords: Cell Automata, GrowCut Algorithm, Image Segmentation, Mahalanobis Distance, Mathematical Morphology, Secondary Watershed

References

[1] GUPTA P, SAXENA S, SINGH S, et al. Color image segmentation: a state of the art survey [J]. International Journal of Computational Intelligence Research, 2012, 8(1): 17-25.

[2] Wen Junling, Yan Zhuangzhi, Sun Yubiao, Lin Xiaoman. Image segmentation of integrated edge and region information by lattice Boltzmann model [J]. Journal of Jiangsu University(Natural Science Edition) , 2013, 34(6): 687-692.

[3] IVANOVICI M, RICHARD N, PAULUS D. Color image segmentation [M]/Advanced Color Image Processing and Analysis. Springer New York, 2013: 219-277.

DOI: 10.1007/978-1-4419-6190-7_8

[4] Zhang yi, Applied research in image segmentation used by the algorithm of watershed [D]. Guangdong University of Technology, (2013).

[5] VEZHNEVETS V, KONOUCHINE V. GrowCut: Interactive multi-label ND image segmentation by Cellular Automata[C]/proc. of Graphicon. 2005, Novosibirsk Akademgorodok, Russia: [s. n. ] 2006: 231-234.

[6] ARNDT O J, SCHEUERMANN B, ROSENHAHN B. Region Cut, -Interactive multi-label segmentation utilizing cellular automaton[C]/2013 IEEE Workshop on Applications of Computer Vision (WACV). IEEE, 2013: 309-316.

DOI: 10.1109/wacv.2013.6475034

[7] GHOSH P, ANTANI S K, LONG L R, et al. Unsupervised Grow-Cut: cellular automata-based medical Image segmentation[C]/Healthcare Informatics, Imaging and Systems Biology (HISB), 2011 First IEEE International Conference on. IEEE, 2011: 40-47.

DOI: 10.1109/hisb.2011.44

[8] Phan R, Androutsos D. Interactive video GrowCut: A semi-automated video object segmentation framework using cellular automata [C]/Electrical and Computer Engineering (CCECE), 2011 24th Canadian Conference on. IEEE, 2011: 000081-000084.

DOI: 10.1109/ccece.2011.6030413

[9] ROTHER C, KOLMOGOROV V, BLAKE A. Grabcut: Interactive foreground extraction using iterated graph cuts[C]/ACM Transactions on Graphics (TOG). ACM, 2004, 23(3): 309-314.

DOI: 10.1145/1015706.1015720

[10] Lan hong, Min-lequan. Interactive Segmentation Algorithm Optimized by Multi-threshold with Application in Medical Images [J]. Journal of Computer Applications, 2013, 33(5): 1435-1438.

DOI: 10.3724/sp.j.1087.2013.01435

[11] BIENIECKI W. Over segmentation avoidance in watershed-based algorithms for color images [C]/modern Problems of Radio Engineering, Telecommunications and Computer Science, 2004. Proceedings of the International Conference. IEEE, 2004: 169-172.

[12] CHEN Bin, ZOU Xian-yong, ZHU Wen-jing. Eliminating outlier samples in near-infrared model by method of PCA-mahalanobis distance [J]. Journal of Jiangsu University (Natural Science Edition), 2008, 29(4): 277-279.

[13] von NEUMANN J. Theory of self-reproducing automata [M]. Urbana-Champaign, Illinois, USA: University of Illinois Press, (1966).

[14] TAO W, JIN H, ZHANG Y. Color image segmentation based on mean shift and normalized cuts [J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 2007, 37(5): 1382-1389.

DOI: 10.1109/tsmcb.2007.902249

[15] Xu Xiao-li, Lu Zhi-mao, Zhang ge-sen, Li chun, and Zhang qi. Color Image Segmentation Based on Improved Affinity Propagation Clustering, Journal of Computer-Aided Design & Computer Graphics, 2012, 24(4): 514-519.

[16] Lu Zhi-mao, Xu Xiao-li, Fan Dong-mei, Li Hai-yan, Color Image Segmentation Based on Secondary Watershed and Ncut Algorithm, Journal of Huazhong University of Science and Technology (Nature Science), 2011, 39(z2): 95-98.