Texture is an important cue in region-based segmentation of images.
We provide an insight into the development of a new set of distortion-invariant
texture operators. These “circular-Mellin” operators are invariant
to both scale and orientation of the target and represent the spectral
decomposition of the image scene in the polar-log coordinate system.
Coupled with the unique shift invariance property of the correlator
architecture, we show that these circular-Mellin operators can be
used for rotation-and scale-invariant feature extraction. We note
that while these feature extractors have a functional form that is
similar to the Gabor operators, they have distortion-invariant characteristics
unlike the Gabor functions that make them more suitable for texture
segmentation. A detailed analytical description of these operators
and segmentation results to highlight their salient properties are
presented
%0 Journal Article
%1 RavichandranDec1995
%A Ravichandran, G.
%A Trivedi, M.M.
%D 1995
%I IEEE Computer Society
%K Gabor analysis, analysisGabor architecture, based characteristics, circular-Mellin coordinate correlation correlator decomposition, distortion extraction, feature features, functional functions, image invariance invariant methods, operators, polar-log property, region representation, rotation scale segmentation segmentation, shift spectral system, texture texture,
%N 12
%P 1629--1640
%R 10.1109/83.475513
%T Circular-Mellin features for texture segmentation
%V 4
%X Texture is an important cue in region-based segmentation of images.
We provide an insight into the development of a new set of distortion-invariant
texture operators. These “circular-Mellin” operators are invariant
to both scale and orientation of the target and represent the spectral
decomposition of the image scene in the polar-log coordinate system.
Coupled with the unique shift invariance property of the correlator
architecture, we show that these circular-Mellin operators can be
used for rotation-and scale-invariant feature extraction. We note
that while these feature extractors have a functional form that is
similar to the Gabor operators, they have distortion-invariant characteristics
unlike the Gabor functions that make them more suitable for texture
segmentation. A detailed analytical description of these operators
and segmentation results to highlight their salient properties are
presented
@article{RavichandranDec1995,
abstract = {Texture is an important cue in region-based segmentation of images.
We provide an insight into the development of a new set of distortion-invariant
texture operators. These “circular-Mellin” operators are invariant
to both scale and orientation of the target and represent the spectral
decomposition of the image scene in the polar-log coordinate system.
Coupled with the unique shift invariance property of the correlator
architecture, we show that these circular-Mellin operators can be
used for rotation-and scale-invariant feature extraction. We note
that while these feature extractors have a functional form that is
similar to the Gabor operators, they have distortion-invariant characteristics
unlike the Gabor functions that make them more suitable for texture
segmentation. A detailed analytical description of these operators
and segmentation results to highlight their salient properties are
presented},
added-at = {2011-03-27T19:35:34.000+0200},
author = {Ravichandran, G. and Trivedi, M.M.},
biburl = {https://www.bibsonomy.org/bibtex/2354e6fae1ac86ce6c1f50cb26c6a287b/cocus},
doi = {10.1109/83.475513},
file = {:./00475513.pdf:PDF},
interhash = {f385d5068f51f545eacc52a2674ea5c7},
intrahash = {354e6fae1ac86ce6c1f50cb26c6a287b},
issn = {1057-7149},
journaltitle = {#ieeetip#},
keywords = {Gabor analysis, analysisGabor architecture, based characteristics, circular-Mellin coordinate correlation correlator decomposition, distortion extraction, feature features, functional functions, image invariance invariant methods, operators, polar-log property, region representation, rotation scale segmentation segmentation, shift spectral system, texture texture,},
location = {#ieeeaddr#},
month = dec,
number = 12,
pages = {1629--1640},
publisher = {{IEEE} Computer Society},
timestamp = {2011-03-27T19:35:42.000+0200},
title = {Circular-Mellin features for texture segmentation},
volume = 4,
year = 1995
}