Foreground/background segmentation of color images by integration of multiple cues

Author

Huang, Qian ; Dam, Bernard ; Steele, D. ; Ashley, J. ; Niblack, W.

Author_Institution

Siemens Corp. Res. Inc., Princeton, NJ, USA

Volume

1

fYear

1995

fDate

23-26 Oct 1995

Firstpage

246

Abstract

This research addresses the issue of automatically segmenting color images into foreground (F) and back-ground (B) regions with the assumption that background regions are relatively smooth but may have gradually varying colors or be slightly textured. A multi-level segmentation scheme is used that involves color clustering, unsupervised segmentation using MDL (minimum description length) principle, edge-based F/B separation, and integrated F/B segmentation. The approach has been tested on more than 100 images. Some of the experimental results are presented

Keywords

edge detection; image colour analysis; image segmentation; color clustering; color images; edge-based separation; foreground/background segmentation; integration; minimum description length; multi-level segmentation scheme; multiple cues; textured images; unsupervised segmentation; Algorithm design and analysis; Clustering algorithms; Color; Educational institutions; Image databases; Image segmentation; Lead time reduction; Merging; Polynomials; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1995. Proceedings., International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-8186-7310-9

Type

conf

DOI

10.1109/ICIP.1995.529692

Filename

529692