Using Prior Shapes in Geometric Active Contours in a Variational Framework

  • Authors:

  • Yunmei Chen;Hemant D. Tagare;Sheshadri Thiruvenkadam;Feng Huang;David Wilson;Kaundinya S. Gopinath;Richard W. Briggs;Edward A. Geiser

  • Affiliations:

  • Department of Mathematics, University of Florida, Gainesville, FL 32611, USA. yun@math.ufl.edu;Department of Diagnostic Radiology and Department of Electrical Engineering, Yale University, New Haven, CT 06520, USA. hemant.tagare@yale.edu;Department of Mathematics, University of Florida, Gainesville, FL 32611, USA. sheshad@math.ufl.edu;Department of Mathematics, University of Florida, Gainesville, FL 32611, USA. feng@math.ufl.edu;Department of Mathematics, University of Florida, Gainesville, FL 32611, USA. dcw@math.ufl.edu;Department of Radiology, University of Florida, Gainesville, FL 32611, USA. gopi@ufbi.ufl.edu;Department of Radiology, University of Florida, Gainesville, FL 32611, USA. rbriggs@ufl.edu;Division of Cardiology, Department of Medicine, University of Florida, Gainesville, FL 32610, USA. Geiseea@medicine.ufl.edu

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we report an active contour algorithm that is capable of using prior shapes. The energy functional of the contour is modified so that the energy depends on the image gradient as well as the prior shape. The model provides the segmentation and the transformation that maps the segmented contour to the prior shape. The active contour is able to find boundaries that are similar in shape to the prior, even when the entire boundary is not visible in the image (i.e., when the boundary has gaps). A level set formulation of the active contour is presented. The existence of the solution to the energy minimization is also established.We also report experimental results of the use of this contour on 2d synthetic images, ultrasound images and fMRI images. Classical active contours cannot be used in many of these images.