RI | Publications | Concurrent Object Segmentation and Recognition with Graph Partitioning

Text only version of this site

Concurrent Object Segmentation and Recognition with Graph Partitioning
S. Yu, R. Gross, and J. Shi
Proceedings of Neural Information Processing Systems (NIPS '02), November, 2002.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Download [Help]

Adobe portable document format (pdf) [680 KB]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

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 and 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. This process is integrated with the pixel grouping based on low-level feature similarity, through pixel-patch interactions and patch competition that is encoded as constraints in the solution space. The globally optimal partition is obtained by solving a constrained eigenvalue problem. We demonstrate that the resulting object segmentation eliminates local false positives at the high level of part detection, while overcoming occlusion and weak contours at the low level of edge detection.

Notes

Associated center: VASC

Number of pages: 8

Text Reference

S. Yu, R. Gross, and J. Shi, "Concurrent Object Segmentation and Recognition with Graph Partitioning," Proceedings of Neural Information Processing Systems (NIPS '02), November, 2002.

BibTeX Reference

@inproceedings{Yu_2002_4383,
   author = "Stella Yu and Ralph Gross and Jianbo Shi",
   title = "Concurrent Object Segmentation and Recognition with Graph Partitioning",
   booktitle = "Proceedings of Neural Information Processing Systems (NIPS '02)",
   month = "November",
   year = "2002"
}