BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:lm77

The blue social bookmark and publication sharing system.

entry of lm77 and 1 other user:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

PicToSeek: combining color and shape invariant features for image retrieval

by: T. Gevers, and A.W.M. Smeulders

In: IEEE Transactions on Image Processing, Vol. 9, Nr. 1 (January 2000) , p. 102--119.

Abstract

We aim at combining color and shape invariants for indexing and retrieving images. To this end, color models are proposed independent of the object geometry, object pose, and illumination. From these color models, color invariant edges are derived from which shape invariant features are computed. Computational methods are described to combine the color and shape invariants into a unified high-dimensional invariant feature set for discriminatory object retrieval. Experiments have been conducted on a database consisting of 500 images taken from multicolored man-made objects in real world scenes. From the theoretical and experimental results it is concluded that object retrieval based on composite color and shape invariant features provides excellent retrieval accuracy. Object retrieval based on color invariants provides very high retrieval accuracy whereas object retrieval based entirely on shape invariants yields poor discriminative power. Furthermore, the image retrieval scheme is highly robust to partial occlusion, object clutter and a change in the object's pose. Finally, the image retrieval scheme is integrated into the PicToSeek system on-line at http://www.wins.uva.nl/research/isis/PicToSeek/ for searching images on the World Wide Web.

Description

Dissertation

BibTeX record

@article{gevers:ieee2000,
  abstract = {We aim at combining color and shape invariants for indexing and retrieving
	images. To this end, color models are proposed independent of the
	object geometry, object pose, and illumination. From these color
	models, color invariant edges are derived from which shape invariant
	features are computed. Computational methods are described to combine
	the color and shape invariants into a unified high-dimensional invariant
	feature set for discriminatory object retrieval. Experiments have
	been conducted on a database consisting of 500 images taken from
	multicolored man-made objects in real world scenes. From the theoretical
	and experimental results it is concluded that object retrieval based
	on composite color and shape invariant features provides excellent
	retrieval accuracy. Object retrieval based on color invariants provides
	very high retrieval accuracy whereas object retrieval based entirely
	on shape invariants yields poor discriminative power. Furthermore,
	the image retrieval scheme is highly robust to partial occlusion,
	object clutter and a change in the object's pose. Finally, the image
	retrieval scheme is integrated into the PicToSeek system on-line
	at http://www.wins.uva.nl/research/isis/PicToSeek/ for searching
	images on the World Wide Web.},
  added-at = {2007-12-04T05:18:34.000+0100},
  annote = {Paper + PDF},
  author = {Gevers, T. and Smeulders, A.W.M.},
  biburl = {http://www.bibsonomy.org/bibtex/23b2394c8268479eba4d53a385f8612a4/lm77},
  description = {Dissertation},
  interhash = {4f3194edf8d7703679402c44868760a0},
  intrahash = {3b2394c8268479eba4d53a385f8612a4},
  journal = {IEEE Transactions on Image Processing},
  keywords = {Feedback Implementation, PicToSeek, Relevance},
  month = {January},
  number = 1,
  pages = {102--119},
  timestamp = {2007-12-04T05:18:34.000+0100},
  title = {Pic{T}o{S}eek: combining color and shape invariant features for image
	retrieval},
  volume = 9,
  year = 2000
}

Endnote record

%0 Journal Article
%1 gevers:ieee2000
%A Gevers, T.
%A Smeulders, A.W.M.
%D 2000
%J IEEE Transactions on Image Processing
%K 
%N 1
%P 102--119
%T Pic{T}o{S}eek: combining color and shape invariant features for image
	retrieval
%V 9
%X We aim at combining color and shape invariants for indexing and retrieving
	images. To this end, color models are proposed independent of the
	object geometry, object pose, and illumination. From these color
	models, color invariant edges are derived from which shape invariant
	features are computed. Computational methods are described to combine
	the color and shape invariants into a unified high-dimensional invariant
	feature set for discriminatory object retrieval. Experiments have
	been conducted on a database consisting of 500 images taken from
	multicolored man-made objects in real world scenes. From the theoretical
	and experimental results it is concluded that object retrieval based
	on composite color and shape invariant features provides excellent
	retrieval accuracy. Object retrieval based on color invariants provides
	very high retrieval accuracy whereas object retrieval based entirely
	on shape invariants yields poor discriminative power. Furthermore,
	the image retrieval scheme is highly robust to partial occlusion,
	object clutter and a change in the object's pose. Finally, the image
	retrieval scheme is integrated into the PicToSeek system on-line
	at http://www.wins.uva.nl/research/isis/PicToSeek/ for searching
	images on the World Wide Web.
%Z Paper + PDF