Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[JKH+03]  Non-Photorealistic Rendering and Content-Based Image Retrieval

Ji:2003:NCB (In proceedings)
Author(s)Ji X., Kato Z. and Huang Z.
Title« Non-Photorealistic Rendering and Content-Based Image Retrieval »
InProceedings of Pacific Graphics 2003
Editor(s)Jon Rokne and Reinhard Klein and Wenping Wang
Page(s)153--160
Year2003
OrganizationIEEE Computer Society
PublisherIEEE
AddressLos Alamitos, CA
Editor(s)Jon Rokne and Reinhard Klein and Wenping Wang

Abstract
In this paper, we will show how non-photorealistic rendering (NPR) can take a new role in content-based image retrieval (CBIR). The proposed CBIR method applies a novel image similarity measure: Unlike traditional features like color, texture, or shape, our measure is based on a painted representation of the original image. This is produced by a stochastic paintbrush algorithm which simulates a painting process. We use the stroke parameters (color, size, orientation, and location) as features and similarity is measured by matching strokes of a pair of images. The advantage of our approach is that it provides information not only about the color content but also about the structural properties of an image without the segmentation of the image. Experimental results show that the CBIR method using paintbrush features has higher retrieval rate than traditional methods using color or texture features only.

BibTeX code
@inproceedings{Ji:2003:NCB,
  optnote = {},
  author = {Xiaowen Ji and Zoltan Kato and Zhiyong Huang},
  optkey = {},
  optannote = {},
  optseries = {},
  editor = {Jon Rokne and Reinhard Klein and Wenping Wang},
  localfile = {papers/Ji.2003.NCB.pdf},
  address = {Los Alamitos, CA},
  publisher = {IEEE},
  organization = {IEEE Computer Society},
  doi = {http://dx.doi.org/10.1109/PCCGA.2003.1238257},
  optmonth = {},
  optcrossref = {},
  booktitle = {Proceedings of Pacific Graphics 2003},
  optvolume = {},
  title = {{N}on-{P}hotorealistic {R}endering and {C}ontent-{B}ased {I}mage
           {R}etrieval},
  optnumber = {},
  abstract = {In this paper, we will show how non-photorealistic rendering (NPR)
              can take a new role in content-based image retrieval (CBIR). The
              proposed CBIR method applies a novel image similarity measure:
              Unlike traditional features like color, texture, or shape, our
              measure is based on a painted representation of the original
              image. This is produced by a stochastic paintbrush algorithm which
              simulates a painting process. We use the stroke parameters (color,
              size, orientation, and location) as features and similarity is
              measured by matching strokes of a pair of images. The advantage of
              our approach is that it provides information not only about the
              color content but also about the structural properties of an image
              without the segmentation of the image. Experimental results show
              that the CBIR method using paintbrush features has higher
              retrieval rate than traditional methods using color or texture
              features only.},
  year = {2003},
  pages = {153--160},
}

 Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

Submit a bug

This document was generated by bib2html 3.3.
Copyright © 1998-05 Stéphane GALLAND (under the GNU General Public License)

Valid HTML 4.01!Valid CSS!