Please use this identifier to cite or link to this item:
Title: Segmentation of color images using a two-stage self-organizing network
Authors: Ong, S.H. 
Yeo, N.C.
Lee, K.H. 
Venkatesh, Y.V. 
Cao, D.M.
Keywords: Artificial neural network
Color clustering
Color image segmentation
Self-organizing map
Issue Date: 1-Apr-2002
Citation: Ong, S.H., Yeo, N.C., Lee, K.H., Venkatesh, Y.V., Cao, D.M. (2002-04-01). Segmentation of color images using a two-stage self-organizing network. Image and Vision Computing 20 (4) : 279-289. ScholarBank@NUS Repository.
Abstract: We propose a two-stage hierarchical artificial neural network for the segmentation of color images based on the Kohonen self-organizing map (SOM). The first stage of the network employs a fixed-size two-dimensional feature map that captures the dominant colors of an image in an unsupervised mode. The second stage combines a variable-sized one-dimensional feature map and color merging to control the number of color clusters that is used for segmentation. A post-processing noise-filtering stage is applied to improve segmentation quality. Experiments confirm that the self-learning ability, fault tolerance and adaptability of the two-stage SOM lead to a good segmentation results. © 2002 Elsevier Science B.V. All rights reserved.
Source Title: Image and Vision Computing
ISSN: 02628856
DOI: 10.1016/S0262-8856(02)00021-5
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Nov 19, 2018


checked on Nov 19, 2018

Page view(s)

checked on Nov 17, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.