Summary: Object Boundary Segmentation Using Graph Cuts Based Active Contours
+ Ning Xu # Ravi Bansal + Narendra Ahuja
+ Beckman Institute and ECE Department # Imaging and Visualization Department,
University of Illinois at Urbana­Champaign Siemens Corporate Research
405 N. Mathews Ave., Urbana, IL 61801 755 College Road East, Princeton, NJ 08540
{ningxu,ahuja}@vision.ai.uiuc.edu ravi@scr.siemens.com
Abstract
In this paper we propose an iterative graph cuts based ac­
tive contours approach to segment an object boundary out
of background. Given an initial boundary nearby the object,
the graph cuts based active contour can iteratively deform
to the object boundary even if there are large discontinu­
ities and noise. In each iteration, the area of interest is
a certain neighborhood of the previously estimated bound­
ary. The problem is formulated as a multi­source multi­
sink s - t minimum cut problem in that neighborhood and
solved using node identification. The result of each step is
globally optimal within the area of interest. On one hand,
this area of interest enables the active contour to break
away from the constraints of previously estimated boundary

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

Collections: Computer Technologies and Information Sciences; Engineering