Title:	Active contours on statistical manifolds and texture segmentation
Author(s):	Lee, Sang-Mook; Abbott, A. Lynn; Clark, Neil A.; Araman, Philip A.
Date:	2005
Source:	In: 2005 International Conference on Image Processing (ICIP): September 11-14, 2005, Genova, Italy. Piscataway, NJ: Institute of Electrical and Electronics Engineers: 828-831
Description:	A new approach to active contours on statistical manifolds is presented. The statistical manifolds are 2- dimensional Riemannian manifolds that are statistically defined by maps that transform a parameter domain onto a set of probability density functions. In this novel framework, color or texture features are measured at each image point and their statistical characteristics are estimated. This is different from statistical representation of bounded regions. A modified Kullback-Leibler divergence, that measures dissimilarity between two density distributions, is added to the statistical manifolds so that a geometric interpretation of the manifolds becomes possible. With this framework, we can formulate a metric tensor on the statistical manifolds. Then, a geodesic active contour is evolved with the aid of the metric tensor. We show that the statistical manifold framework provides more robust and accurate texture segmentation results.
	View and Print this Publication (802 KB)
Pristine Version:	An uncaptured or "pristine" version of this publication is available. It has not been subjected to OCR (Optical Character Recognition) and therefore does not have any errors in the text. However it is a larger file size and some people may experience long download times. The "pristine" version of this publication is available here: View and Print the PRISTINE copy of this Publication (708 KB)
Publication Notes:	We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information. This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain. Our on-line publications are scanned and captured using Adobe Acrobat. During the capture process some typographical errors may occur. Please contact the SRS Webmaster, srswebmaster@fs.fed.us if you notice any errors which make this publication unuseable.
	Get the latest version of the Adobe Acrobat reader or Acrobat Reader for Windows with Search and Accessibility