Object Based Clustering Using Hybrid Algorithms

Author

Razak, Nor Hafizah Abd ; Manshor, Noridayu ; Rajeswari, Mandava ; Ramachandram, Dhanesh

Author_Institution

Comput. Vision Res. Group, Univ. Sains Malaysia, Penang

fYear

2008

fDate

26-28 Aug. 2008

Firstpage

12

Lastpage

17

Abstract

This paper presents a hybrid algorithm for object based clustering. The algorithm is designed based on hybrid of hierarchical and k-means clustering algorithm. For this work, we used dataset consist of natural imagery collected from PASCAL database 2006 collection and Google images. A collection of low level features image is used to validate the performance of our approach. Experimental results show that hybrid algorithm produced higher accuracy compared to k-means and hierarchical algorithm by up to 25%.

Keywords

image recognition; pattern clustering; visual databases; Google images; PASCAL database 2006 collection; hybrid algorithms; k-means clustering algorithm; natural imagery collected; object based clustering; Algorithm design and analysis; Clustering algorithms; Computer graphics; Computer vision; Data mining; Feature extraction; Humans; Partitioning algorithms; Shape; Visualization; Hierarchical; K-means; hybrid algorithm; object based clustering;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Graphics, Imaging and Visualisation, 2008. CGIV '08. Fifth International Conference on

Conference_Location

Penang

Print_ISBN

978-0-7695-3359-9

Type

conf

DOI

10.1109/CGIV.2008.53

Filename

4626977