A color classification algorithm

Author

Iwata, Kansei ; Marcu, Gabriel

Author_Institution

Graphica Computer Corp., Tokyo, Japan

fYear

1993

fDate

20-22 Oct 1993

Firstpage

726

Lastpage

729

Abstract

The color classification process requires that a color image be partitioned into a set of uniform colored regions. A method of automatic classification of a color picture, based on the advantages of a high-speed binary tree splitting algorithm and completed with a stopping criterion derived from color cluster detection methods, is presented. The histogram of distance of the current color point to the center of the investigated cluster is analyzed to stop the binary splitting algorithm. The color space was divided and labeled accordingly to the closest color cluster or region corresponding to a color of the color set. A dynamic dividing method of the color space was used. A post-processing algorithm makes it possible to filter out the unwanted transition colors by absorption and erosion

Keywords

image classification; image colour analysis; image segmentation; tree data structures; absorption; closest color cluster; color classification algorithm; color cluster detection methods; colour filtering; colour space labelling; dynamic dividing method; erosion; high-speed binary tree splitting algorithm; histogram; image partitioning; post-processing algorithm; stopping criterion; uniform colored regions; unwanted transition colors; Absorption; Algorithm design and analysis; Binary trees; Classification algorithms; Classification tree analysis; Clustering algorithms; Filters; Histograms; Image color analysis; Partitioning algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on

Conference_Location

Tsukuba Science City

Print_ISBN

0-8186-4960-7

Type

conf

DOI

10.1109/ICDAR.1993.395634

Filename

395634