Variable structure neural network for adaptive color clustering

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Color clustering is widely used for color image segmentation, transmission and visualization. However, traditional clustering algorithms have difficulty in adaptive determination of the proper cluster number. In this paper, a variable structure self-organizing map neural network (VSSOM) is proposed to achieve adaptive color clustering. It can provide the suitable cluster number and the palette for generating the clustered color image. The characteristic of the algorithm is that the output neuron of VSSOM is changed from 2 to N based on the defined learning rules during training. When the network converges, its N is the number of color clusters and the palette of clustered image is corresponding to the weights of the network. Experimental results show that the proposed algorithm has the desired ability for color clustering.

Original languageEnglish
Title of host publicationProceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010
Pages248-252
Number of pages5
Publication statusPublished - 2010
Event7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010 - Innsbruck
Duration: 2010 Feb 172010 Feb 19

Other

Other7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010
CityInnsbruck
Period10/2/1710/2/19

Fingerprint

neural network
Color
Neural networks
Self organizing maps
visualization
ability
Image segmentation
Clustering algorithms
learning
Neurons
Visualization
segmentation

Keywords

  • Color clustering
  • Neural network
  • Self-organizing map
  • Variable structure

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Communication

Cite this

Zhang, J., & Furuzuki, T. (2010). Variable structure neural network for adaptive color clustering. In Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010 (pp. 248-252)

Variable structure neural network for adaptive color clustering. / Zhang, Jun; Furuzuki, Takayuki.

Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010. 2010. p. 248-252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, J & Furuzuki, T 2010, Variable structure neural network for adaptive color clustering. in Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010. pp. 248-252, 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010, Innsbruck, 10/2/17.
Zhang J, Furuzuki T. Variable structure neural network for adaptive color clustering. In Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010. 2010. p. 248-252
Zhang, Jun ; Furuzuki, Takayuki. / Variable structure neural network for adaptive color clustering. Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010. 2010. pp. 248-252
@inproceedings{bb923291fe8144c9bae9e61064c286ab,
title = "Variable structure neural network for adaptive color clustering",
abstract = "Color clustering is widely used for color image segmentation, transmission and visualization. However, traditional clustering algorithms have difficulty in adaptive determination of the proper cluster number. In this paper, a variable structure self-organizing map neural network (VSSOM) is proposed to achieve adaptive color clustering. It can provide the suitable cluster number and the palette for generating the clustered color image. The characteristic of the algorithm is that the output neuron of VSSOM is changed from 2 to N based on the defined learning rules during training. When the network converges, its N is the number of color clusters and the palette of clustered image is corresponding to the weights of the network. Experimental results show that the proposed algorithm has the desired ability for color clustering.",
keywords = "Color clustering, Neural network, Self-organizing map, Variable structure",
author = "Jun Zhang and Takayuki Furuzuki",
year = "2010",
language = "English",
isbn = "9780889868236",
pages = "248--252",
booktitle = "Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010",

}

TY - GEN

T1 - Variable structure neural network for adaptive color clustering

AU - Zhang, Jun

AU - Furuzuki, Takayuki

PY - 2010

Y1 - 2010

N2 - Color clustering is widely used for color image segmentation, transmission and visualization. However, traditional clustering algorithms have difficulty in adaptive determination of the proper cluster number. In this paper, a variable structure self-organizing map neural network (VSSOM) is proposed to achieve adaptive color clustering. It can provide the suitable cluster number and the palette for generating the clustered color image. The characteristic of the algorithm is that the output neuron of VSSOM is changed from 2 to N based on the defined learning rules during training. When the network converges, its N is the number of color clusters and the palette of clustered image is corresponding to the weights of the network. Experimental results show that the proposed algorithm has the desired ability for color clustering.

AB - Color clustering is widely used for color image segmentation, transmission and visualization. However, traditional clustering algorithms have difficulty in adaptive determination of the proper cluster number. In this paper, a variable structure self-organizing map neural network (VSSOM) is proposed to achieve adaptive color clustering. It can provide the suitable cluster number and the palette for generating the clustered color image. The characteristic of the algorithm is that the output neuron of VSSOM is changed from 2 to N based on the defined learning rules during training. When the network converges, its N is the number of color clusters and the palette of clustered image is corresponding to the weights of the network. Experimental results show that the proposed algorithm has the desired ability for color clustering.

KW - Color clustering

KW - Neural network

KW - Self-organizing map

KW - Variable structure

UR - http://www.scopus.com/inward/record.url?scp=77954579134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954579134&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780889868236

SP - 248

EP - 252

BT - Proceedings of the 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2010

ER -