nips nips2002 nips2002-57 nips2002-57-reference knowledge-graph by maker-knowledge-mining

57 nips-2002-Concurrent Object Recognition and Segmentation by Graph Partitioning


Source: pdf

Author: Stella X. Yu, Ralph Gross, Jianbo Shi

Abstract: Segmentation and recognition have long been treated as two separate processes. We propose a mechanism based on spectral graph partitioning that readily combine the two processes into one. A part-based recognition system detects object patches, supplies their partial segmentations as well as knowledge about the spatial configurations of the object. The goal of patch grouping is to find a set of patches that conform best to the object configuration, while the goal of pixel grouping is to find a set of pixels that have the best low-level feature similarity. Through pixel-patch interactions and between-patch competition encoded in the solution space, these two processes are realized in one joint optimization problem. The globally optimal partition is obtained by solving a constrained eigenvalue problem. We demonstrate that the resulting object segmentation eliminates false positives for the part detection, while overcoming occlusion and weak contours for the low-level edge detection.


reference text

[1] E. Borenstein and S. Ullman. Class-specific, top-down segmentation. In European Conference on Computer Vision, 2002.

[2] K. Fukunaga. Introduction to statistical pattern recognition. Academic Press, 1990.

[3] S. Mahamud, M. Hebert, and J. Lafferty. Combining simple discriminators for object discrimination. In European Conference on Computer Vision, 2002.

[4] J. Malik, S. Belongie, T. Leung, and J. Shi. Contour and texture analysis for image segmentation. International Journal of Computer Vision, 200l.

[5] D. Marr. Vision. CA: Freeman, 1982.

[6] S. E. Palmer. Vision science: from photons to phenomenology. MIT Press, 1999.

[7] J. Shi and J. Malik. Normalized cuts and image segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 731- 7, June 1997.

[8] H. Sidenbladh and M. Black. Learning image statistics for Bayesian tracking. In International Conference on Computer Vision , 200l.

[9] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In IEEE Conference on Computer Vision and Pattern Recognition, 200l.

[10] S. X. Yu and J. Shi. Grouping with bias. In Neural Information Processing Systems, 2001.