Edge strength functions as shape priors in image segmentation


Erdem E., Erdem A., Tari S.

5th International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2005, St. Augustine, FL, United States Of America, 9 - 11 November 2005, pp.490-502 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1007/11585978_32
  • City: St. Augustine, FL
  • Country: United States Of America
  • Page Numbers: pp.490-502

Abstract

Many applications of computer vision requires segmenting out of an object of interest from a given image. Motivated by unlevel-sets formulation of Raviv, Kiryati and Sochen [8] and statistical formulation of Leventon, Grimson and Faugeras [6], we present a new image segmentation method which accounts for prior shape information. Our method depends on Ambrosio-Tortorelli approximation of Mumford-Shah functional. The prior shape is represented by a by-product of this functional, a smooth edge indicator function, known as the "edge strength function", which provides a distance-like surface for the shape boundary. Our method can handle arbitrary deformations due to shape variability as well as plane Euclidean transformations. The method is also robust with respect to noise and missing parts. Furthermore, this formulation does not require simple closed curves as in a typical level set formulation. © Springer-Verlag Berlin Heidelberg 2005.