10 February 2009 Active contours that grow and compete driven by local region descriptors
Author Affiliations +
Abstract
Region-based active contours are a variational framework for image segmentation. It involves estimating the probability distributions of observed features within each image region. Subsequently, these so-called region descriptors are used to generate forces to move the contour toward real image boundaries. In this paper region descriptors are computed from samples within windows centered on contour pixels and they are named local region descriptors (LRDs). With these descriptors we introduce an equation for contour motion with two terms: growing and competing. This equation yields a novel type of AC that can adjust the behavior of contour pieces to image patches and to the presence of other contours. The quality of the proposed motion model is demonstrated on complex images.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cristina Darolti, Cristina Darolti, Erhardt Barth, Erhardt Barth, Christoph Bodensteiner, Christoph Bodensteiner, Ulrich G. Hofmann, Ulrich G. Hofmann, } "Active contours that grow and compete driven by local region descriptors", Proc. SPIE 7245, Image Processing: Algorithms and Systems VII, 72450F (10 February 2009); doi: 10.1117/12.805983; https://doi.org/10.1117/12.805983
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Beef quality grading using machine vision
Proceedings of SPIE (December 28 2000)
Color transfer algorithm in medical images
Proceedings of SPIE (November 13 2007)
Color Texture Analysis And Synthesis Using Gibbs Random Fields
Proceedings of SPIE (September 04 1989)

Back to Top