Image segmentation and similarity of color-texture objects

Author

Gevers, Theo

Author_Institution

Comput. Sci. Inst., Univ. of Amsterdam, Netherlands

Volume

4

Issue

4

fYear

2002

fDate

12/1/2002 12:00:00 AM

Firstpage

509

Lastpage

516

Abstract

We aim for content-based image retrieval of textured objects in natural scenes under varying illumination and viewing conditions. To achieve this, image retrieval is based on matching feature distributions derived from color invariant gradients. To cope with object cluttering, region-based texture segmentation is applied on the target images prior to the actual image retrieval process. The retrieval scheme is empirically verified on color images taken from textured objects under different lighting conditions.

Keywords

content-based retrieval; image colour analysis; image segmentation; image texture; visual databases; color constancy; color images; color invariance; color invariant gradients; color-texture object similarity; content-based image retrieval; digital libraries; feature distribution matching; illumination conditions; image databases; image retrieval process; image segmentation; image similarity; lighting conditions; natural scenes; object cluttering; region-based texture segmentation; retrieval scheme; target images; textured objects; viewing conditions; Color; Content based retrieval; Histograms; Image databases; Image retrieval; Image segmentation; Information retrieval; Layout; Lighting; Robustness;

fLanguage

English

Journal_Title

Multimedia, IEEE Transactions on

Publisher

ieee

ISSN

1520-9210

Type

jour

DOI

10.1109/TMM.2002.802023

Filename

1176949