DMCA
Contour detection by multiresolution surround inhibition (2006)
| Venue: | in Proc. IEEE Int. Conf. on Image Processing |
| Citations: | 3 - 2 self |
BibTeX
@INPROCEEDINGS{Campisi06contourdetection,
author = {Patrizio Campisi and Nicolai Petkov and Ro Neri},
title = {Contour detection by multiresolution surround inhibition},
booktitle = {in Proc. IEEE Int. Conf. on Image Processing},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In natural images, luminance changes occur both on object contours and on textures. Often, the latter are stronger than the former, thus standard edge detectors fail in isolating object contours from texture. To overcome this problem, we propose a multiresolution contour detector motivated by biological principles. At each scale, texture is suppressed by using a bipolar surround inhibition process. The binary contour map is obtained by a contour selection criterion that is more effective than the classical hysteresis thresholding. Robustness to noise is achieved by Bayesian gradient estimation.
Keyphrases
contour detection multiresolution surround inhibition object contour standard edge detector biological principle natural image bipolar surround inhibition process binary contour map classical hysteresis luminance change multiresolution contour detector bayesian gradient estimation contour selection criterion
