Stella X. Yu : Research : popout

Understanding Popout through Repulsion

Stella X. Yu and Jianbo Shi

IEEE Conference on Computer Vision and Pattern Recognition, Kauai Marriott, Hawaii, USA, 9-15 Dec 2001

Paper (w/ correction) | Slides

Abstract

We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of $15$ objects under clutter and occlusion.

Keywords

image segmentation, figure-ground, object recognition, graph partitioning, constrained optimization

Note

with correction of bounds for infinite regularization: Tab. 2 and Fig. 4