Geodesic Active Contours

  • Authors:

  • Vicent Caselles;Ron Kimmel;Guillermo Sapiro

  • Affiliations:

  • Department of Mathematics and Informatics, University of Illes Balears, 07071 Palma de Mallorca, Spain/ E-mail: dmivca0@ps.uib.es;Department of Electrical Engineering, Technion, I.I.T., Haifa 32000, Israel/ E-mail: ron@tx.technion.ac.il;Hewlett-Packard Labs, 1501 Page Mill Road, Palo Alto, CA 94304/ E-mail: guille@hpl.hp.com

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 1997

Quantified Score

Hi-index 0.04

Visualization

Abstract

A novel scheme for the detection of object boundaries is presented.The technique is based on active contours evolving in timeaccording to intrinsic geometric measures of the image.The evolving contours naturally split and merge,allowing the simultaneous detection ofseveral objects and both interior and exterior boundaries.The proposed approach is based on the relation betweenactive contours and the computation of geodesics or minimal distance curves.The minimal distance curve lays in a Riemannian space whose metric is defined by the image content.This geodesic approach for object segmentation allows to connect classical“snakes” based on energy minimization and geometric activecontours based on the theory of curve evolution.Previous models of geometric active contours are improved,allowing stable boundary detectionwhen their gradients suffer from large variations, including gaps.Formal results concerning existence, uniqueness, stability, andcorrectness of the evolution are presented as well.The scheme was implemented using an efficient algorithm for curve evolution.Experimental results of applying the scheme to real images includingobjects with holes and medical data imagery demonstrate its power.The results may be extended to 3D object segmentation as well.