DMCA
This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON CYBERNETICS 1 Automated Adjustment of Region-Based Active Contour Parameters Using Local
BibTeX
@MISC{Mylona_thisarticle,
author = {Eleftheria A. Mylona and Michalis A. Savelonas and Dimitris Maroulis},
title = {This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON CYBERNETICS 1 Automated Adjustment of Region-Based Active Contour Parameters Using Local },
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—A principled method for active contour (AC) param-eterization remains a challenging issue in segmentation research, with a potential impact on the quality, objectivity, and robust-ness of the segmentation results. This paper introduces a novel framework for automated adjustment of region-based AC regularization and data fidelity parameters. Motivated by an iso-morphism between the weighting factors of AC energy terms and the eigenvalues of structure tensors, we encode local geom-etry information by mining the orientation coherence in edge regions. In this light, the AC is repelled from regions of ran-domly oriented edges and guided toward structured edge regions. Experiments are performed on four state-of-the-art AC models, which are automatically adjusted and applied on benchmark datasets of natural, textured and biomedical images and two image restoration models. The experimental results demonstrate that the obtained segmentation quality is comparable to the one obtained by empirical parameter adjustment, without the cumbersome and time-consuming process of trial and error. Index Terms—Active contours, automated parameterization, structure tensors. I.
Keyphrases
automated adjustment ieee transaction cybernetics future issue edge region structure tensor state-of-the-art ac model segmentation result potential impact biomedical image data fidelity parameter local geom-etry information time-consuming process empirical parameter adjustment active contour segmentation research orientation coherence benchmark datasets principled method ac energy term index term active contour challenging issue novel framework image restoration model segmentation quality experimental result region-based ac regularization
