Image Segmentation Based on Superpixels and Saliency

Abstract:

Image segmentation plays an important role in computer vision and image processing to interpret and analyze an acquired image. Separation of objects or image regions is usually required for high-level image comprehension in practical applications involving visual inspection. In this paper, a novel automatic image segmentation method is proposed. To extract the foreground of the image automatically, we combine saliency model based on superpixels with the affinity propagation clustering algorithm in an unsupervised manner, and use graph cut method to obtain the segmentation results.

• Periodical: Applied Mechanics and Materials (Volumes 701-702)
• Pages: 312-315
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.701-702.312
• Online since: December 2014
• Authors: Qi Chen*, Xing Ben Yang, Yun Hong Chen, Dan Dan Li
• Keywords: Graph Cut, Saliency Model, Superpixel

References

[1] Y. Yue,Q. Shi,G. Hu,J.A. Wang. Proceedings of the IEEE International Conference on Geo informatics. (2011)1–6.

[2] Z. Tu,X. Bai. IEEETrans. PatternAnal. Mach. Intell. (2010) 1744–1757.

[3] Y. Boykov and M. -P. Jolly. In ICCV, (2001).

[4] C. Rother, V. Kolmogorov, and A. Blake. SIGGRAPH, ( 2004).

[5] P. Felzenszwalb and D. Huttenlocher. International Journal of Computer Vision (2004).

[6] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. International Journal of Computer Vision (2010), 88(2): 303–338.

DOI: 10.1007/s11263-009-0275-4

[7] A. Borji, D. N. Sihite, and L. Itti. Vision research( 2013)91: 62–77.

[8] C. Rother, V. Kolmogorov, and A. Blake. In ACM Trans. on Graphics SIGGRAPH, (2004).