A framework is proposed for segmenting image textures by using Gabor filters to detect boundaries between adjacent textured regions. By performing a multi-channel filtering of the input image with a small set of adaptively selected Gabor filters, tuned to underlying textures, feature images are obtained. To reduce the variance of the filter output for better texture boundary detection, a Gaussian post-filter is applied to the Gabor filter response over each channel. Significant local variations in each channel response are detected using a gradient operator, and combined through channel grouping to produce the texture gradient. A subsequent post-processing produces expected texture boundaries. The effectiveness of the proposed technique is demonstrated through experiments on synthetic and natural textures.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Bertin Rodolphe OKOMBI-DIBA, Juichi MIYAMICHI, Kenji SHOJI, "Texture Boundary Detection Using 2-D Gabor Elementary Functions" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 6, pp. 727-740, June 2001, doi: .
Abstract: A framework is proposed for segmenting image textures by using Gabor filters to detect boundaries between adjacent textured regions. By performing a multi-channel filtering of the input image with a small set of adaptively selected Gabor filters, tuned to underlying textures, feature images are obtained. To reduce the variance of the filter output for better texture boundary detection, a Gaussian post-filter is applied to the Gabor filter response over each channel. Significant local variations in each channel response are detected using a gradient operator, and combined through channel grouping to produce the texture gradient. A subsequent post-processing produces expected texture boundaries. The effectiveness of the proposed technique is demonstrated through experiments on synthetic and natural textures.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_6_727/_p
Copy
@ARTICLE{e84-d_6_727,
author={Bertin Rodolphe OKOMBI-DIBA, Juichi MIYAMICHI, Kenji SHOJI, },
journal={IEICE TRANSACTIONS on Information},
title={Texture Boundary Detection Using 2-D Gabor Elementary Functions},
year={2001},
volume={E84-D},
number={6},
pages={727-740},
abstract={A framework is proposed for segmenting image textures by using Gabor filters to detect boundaries between adjacent textured regions. By performing a multi-channel filtering of the input image with a small set of adaptively selected Gabor filters, tuned to underlying textures, feature images are obtained. To reduce the variance of the filter output for better texture boundary detection, a Gaussian post-filter is applied to the Gabor filter response over each channel. Significant local variations in each channel response are detected using a gradient operator, and combined through channel grouping to produce the texture gradient. A subsequent post-processing produces expected texture boundaries. The effectiveness of the proposed technique is demonstrated through experiments on synthetic and natural textures.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - Texture Boundary Detection Using 2-D Gabor Elementary Functions
T2 - IEICE TRANSACTIONS on Information
SP - 727
EP - 740
AU - Bertin Rodolphe OKOMBI-DIBA
AU - Juichi MIYAMICHI
AU - Kenji SHOJI
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2001
AB - A framework is proposed for segmenting image textures by using Gabor filters to detect boundaries between adjacent textured regions. By performing a multi-channel filtering of the input image with a small set of adaptively selected Gabor filters, tuned to underlying textures, feature images are obtained. To reduce the variance of the filter output for better texture boundary detection, a Gaussian post-filter is applied to the Gabor filter response over each channel. Significant local variations in each channel response are detected using a gradient operator, and combined through channel grouping to produce the texture gradient. A subsequent post-processing produces expected texture boundaries. The effectiveness of the proposed technique is demonstrated through experiments on synthetic and natural textures.
ER -