Class-Specific, Top-Down Segmentation
In this paper we present a novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images). The approach is different from bottom-up segmentation methods that primarily use the continuity of grey-level, texture, and bounding contours. We show that the method leads to markedly improved segmentation results and can deal with significant variation in shape and varying backgrounds. We discuss the relative merits of class-specific and general image-based segmentation methods and suggest how they can be usefully combined.
KeywordsGrouping and segmentation Figure-ground Top-down processing Object classification
Unable to display preview. Download preview PDF.
- 3.R. Duda, P. Hart, and D. Stork. Pattern classification, 2001.Google Scholar
- 6.T. Leung and J. Malik. Contour continuity in region based image segmentation. In Fifth Euro. Conf. Computer Vision, Freiburg, Germany, 1998.Google Scholar
- 7.D. Mumford and J. Shah. Boundary detection by minimizing functionals. In IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, 1985.Google Scholar
- 13.E. Sali and S. Ullman. Combining class-specific fragments for object classification. In Proc. 10th British Machine Vision Conference, volume 1, pages 203–213, 1999.Google Scholar
- 14.E. Sharon, A. Brandt, and R. Basri. Fast multiscale image segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 70–77, South Carolina, 2000.Google Scholar
- 15.J. Shi and J. Malik. Normalized cuts and image segmentation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 731–737, 1997.Google Scholar
- 17.S. Ullman, E. Sali, and M. Vidal-Naquet. A fragment based approach to object representation and classification. In Proc. of 4th international workshop on visual form, Capri, Italy, 2001.Google Scholar
- 18.A. Yuille and P. Hallinan. Deformable templates. In A. Blake and A. Yuille, editors, Active Vision, pages 21–38, MIT press, 1992.Google Scholar