Image Segmentation by Pre-Labeling Based on Part-Based Model

Abstract:

Interactive segmentation with graph cuts has become very popular and many priors have been introduced into graph cuts to improve the results. This paper proposed a method which uses the deformable part-based model to pre-label the seeds. First the deformable part-based model finds out the bounding box, then we can pre-label the seed point based on the assumption of compact shape. Our results show that our method can get more accurate result especially the appearance of the object and background are similar and the shape is compact.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 4206-4210
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.4206
• Online since: May 2014
• Authors: Wei Liu, Xue Jun Xu*
• Keywords: Deformable Part-Based Models, Graph Cuts, Pre-Labeling

References

[1] Y. Boykov, M. -P. Jolly: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images, in: ICCV, 2001, p.105–112.

DOI: 10.1109/iccv.2001.937505

[2] C. Rother, V. Kolmogorov, A. Blake: grabcut,: interactive foreground extraction using iterated graph cuts, ACM Trans. Graph. 23 (3) (2004) 309–314.

DOI: 10.1145/1015706.1015720

[3] O. Veksler: Star shape prior for graph-cut image segmentation, in: ECCV (3), 2008, p.454–467.

DOI: 10.1007/978-3-540-88690-7_34

[4] G. G. Slabaugh, G. B. Unal: Graph cuts segmentation using an elliptical shape prior, in: ICIP (2), 2005, p.1222–1225.

DOI: 10.1109/icip.2005.1530282

[5] V. S. Lempitsky, P. Kohli, C. Rother, T. Sharp: Image segmentation with a bounding box prior, in: ICCV, 2009, p.277–284.

DOI: 10.1109/iccv.2009.5459262

[6] M. E. Leventon, W. E. L. Grimson, O. D. Faugeras: Statistical shape influence in geodesic active contours, in: CVPR, 2000, p.1316–1323.

DOI: 10.1109/cvpr.2000.855835

[7] A. Tsai, A. J. Yezzi, W. M. W. III, C. M. Tempany, D. Tucker, A. C. Fan,W. E. L. Grimson, A. S. Willsky: Model-based curve evolution technique for image segmentation, in: CVPR (1), 2001, p.463–468.

DOI: 10.1109/cvpr.2001.990511

[8] M. Rousson, N. Paragios: Shape priors for level set representations, in: ECCV (2), 2002, p.78–92.

DOI: 10.1007/3-540-47967-8_6

[9] V. S. Lempitsky, A. Blake, C. Rother: Image segmentation by branch-and-mincut, in: ECCV (4), 2008, p.15–29.

DOI: 10.1007/978-3-540-88693-8_2

[10] D. Cremers, F. R. Schmidt, F. Barthel: Shape priors in variational image segmentation: Convexity, lipschitz continuity and globally optimal solutions, in: CVPR, (2008).

DOI: 10.1109/cvpr.2008.4587446

[11] P. F. Felzenszwalb, D. P. Huttenlocher: Pictorial structures for object recognition, International Journal of Computer Vision 61 (1) (2005) 55–79.

DOI: 10.1023/b:visi.0000042934.15159.49

[12] B. Yangel, D. Vetrov: Image segmentation with a shape prior based on simplified skeleton, in: EMMCVPR, 2011, p.247–260.

[13] P. F. Felzenszwalb, R. B. Girshick, D. A. McAllester, D. Ramanan: Object detection with discriminatively trained part-based models, IEEE Trans. Pattern Anal. Mach. Intell. 32 (9) (2010) 1627–1645.

DOI: 10.1109/tpami.2009.167

[14] V. Kolmogorov, R. Zabih: What energy functions can be minimized via graph cuts?, IEEE Trans. Pattern Anal. Mach. Intell. 26 (2) (2004) 147–159.

DOI: 10.1109/tpami.2004.1262177

[15] O. Veksler: Stereo correspondence with compact windows via minimum ratio cycle, IEEE Trans. Pattern Anal. Mach. Intell. 24 (12) (2002) 1654–1660.

DOI: 10.1109/tpami.2002.1114859

[16] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, A. Zisserman, The PASCAL Visual Object Classes Challenge 2009 (VOC2009) Results, http: /www. pascal-network. org.

DOI: 10.1007/s11263-009-0275-4

[17] N. Dalal, B. Triggs: Histograms of oriented gradients for human detection, in: CVPR (1), 2005, p.886–893.