Center for Human Modeling and Simulation

Contour cut: identifying salient contours in images by solving a Hermitian eigenvalue problem

Ryan Kennedy, University of Pennsylvania
Jean H. Gallier, University of Pennsylvania
Jianbo Shi, University of Pennsylvania

Document Type Conference Paper

Kennedy, R., Gallier, J., & Shi, J. IEEE Conference on Computer Vision and Pattern Recognition. 2011.

Abstract

The problem of finding one-dimensional structures in images and videos can be formulated as a problem of searching for cycles in graphs. In [11], an untangling-cycle cost function was proposed for identifying persistent cycles in a weighted graph, corresponding to salient contours in an image. We have analyzed their method and give two significant improvements. First, we generalize their cost function to a contour cut criterion and give a computational solution by solving a family of Hermitian eigenvalue problems. Second, we use the idea of a graph circulation, which ensures that each node has a balanced in- and out-flow and permits a natural random-walk interpretation of our cost function. We show that our method finds far more accurate contours in images than [11]. Furthermore, we show that our method is robust to graph compression which allows us to accelerate the computation without loss of accuracy

 

Date Posted: 11 July 2012