skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: NONCONVEX REGULARIZATION FOR IMAGE SEGMENTATION

Authors:
 [1];  [1]
  1. Los Alamos National Laboratory
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1211587
Report Number(s):
LA-UR-07-1033
DOE Contract Number:
AC52-06NA25396
Resource Type:
Conference
Resource Relation:
Conference: 2007 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, COMPUTER VISION, AND PATTERN RECOGNITION ; 200706 ; LAS VEGAS
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS

Citation Formats

CHARTRAND, RICK, and STANEVA, VALENTINA. NONCONVEX REGULARIZATION FOR IMAGE SEGMENTATION. United States: N. p., 2007. Web.
CHARTRAND, RICK, & STANEVA, VALENTINA. NONCONVEX REGULARIZATION FOR IMAGE SEGMENTATION. United States.
CHARTRAND, RICK, and STANEVA, VALENTINA. Thu . "NONCONVEX REGULARIZATION FOR IMAGE SEGMENTATION". United States. doi:. https://www.osti.gov/servlets/purl/1211587.
@article{osti_1211587,
title = {NONCONVEX REGULARIZATION FOR IMAGE SEGMENTATION},
author = {CHARTRAND, RICK and STANEVA, VALENTINA},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Feb 15 00:00:00 EST 2007},
month = {Thu Feb 15 00:00:00 EST 2007}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • The authors show that using a nonconvex penalty term to regularize image reconstruction can substantially improve the preservation of object shapes. The commonly-used total-variation regularization, {integral}|{del}u|, penalizes the length of the object edges. They show that {integral}|{del}u|{sup p}, 0 < p < 1, only penalizes edges of dimension at least 2-p, and thus finite-length edges not at all. We give numerical examples showing the resulting improvement in shape preservation.
  • This paper extends a recent image-dependent regularization approach introduced in aiming at edge-preserving smoothing. For that purpose, geodesic distances equipped with a Riemannian metric need to be estimated in local neighbourhoods. By deriving an appropriate metric from the gradient structure tensor, the associated geodesic paths are constrained to follow salient features in images. Following, we design a generalized anisotropic geodesic filter; incorporating not only a measure of the edge strength, like in the original method, but also further directional information about the image structures. The proposed filter is particularly efficient at smoothing heterogeneous areas while preserving relevant structures in multichannelmore » images.« less
  • Image segmentation is a slow but fundamental process in many image processing and computer vision systems. A pipeline architecture is presented. The pipeline uses eight processors and a simple one-pass segmentation algorithm to speed up image segmentation by two orders of magnitude. 8 references.
  • Image segmentation is a standard low-level task in computer vision. We demonstrate how the segmentation of seismic images can assist in geologic interpretation. An image segmentation technique is applied to images of the acoustic impedance. A salient feature of the resulting segments is that the hydrocarbon-bearing regions are characterized by a finer segmentation than the other regions. A modified apparent polarity attribute is introduced, and images of this attribute are segmented. The boundaries of the resulting segments pass through the minima and maxima of the acoustic impedance in a manner that allows us to segment the acoustic impedance image intomore » layers of high and low acoustic impedance. Our methods can assist in segmentation of acoustic impedance images according to lithology or geologic facies.« less