A comparison of some clustering techniques via color segmentation

Author

Agarwal, Shilpa ; Madasu, Shweta ; Hanmandlu, Madasu ; Vasikarla, Shantaram

Author_Institution

Dept. of Electr. Eng., IIT, New Delhi, India

Volume

2

fYear

2005

fDate

4-6 April 2005

Firstpage

147

Abstract

This paper proposes a new improved modified mountain clustering technique. The proposed technique is being compared with some existing techniques such as FCM, Gath-Geva, probabilistic clustering and modified mountain clustering. The performance of all these clustering techniques is compared by applying them to color segmentation in terms of cluster validity and computational complexity.

Keywords

computational complexity; fuzzy set theory; image colour analysis; image segmentation; pattern clustering; probability; Gath-Geva method; cluster validity; computational complexity; fuzzy c-means technique; image color segmentation; modified mountain clustering technique; probabilistic clustering; Clustering algorithms; Clustering methods; Computational complexity; Data mining; Fuzzy set theory; Image retrieval; Image segmentation; Information retrieval; Pattern classification; Set theory; Color segmentation; EM algorithm and cluster validity; Gath-Geva and Fuzzy C-Means clustering techniques; Modified mountain; Probabilistic;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on

Print_ISBN

0-7695-2315-3

Type

conf

DOI

10.1109/ITCC.2005.4

Filename

1425137