Stella X. Yu : Papers / Google Scholar

Concurrent Object Recognition and Segmentation by Graph Partitioning
Stella X. Yu and Ralph Gross and Jianbo Shi
Neural Information Processing Systems, Vancouver, Canada, 9-14 Dec 2002
Paper | Slides

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.

grouping, image segmentation, object recognition, part detection, figure-ground, graph partitioning, bias, attention.