A hierarchical clustering method for color quantization

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

Abstract

In this paper, we propose a hierarchical frequency sensitive competitive learning (HFSCL) method to achieve color quantization (CQ). In HFSCL, the appropriate number of quantized colors and the palette can be obtained by an adaptive procedure following a binary tree structure with nodes and layers. Starting from the root node that contains all colors in an image until all nodes are examined by split conditions, a binary tree will be generated. In each node of the tree, a frequency sensitive competitive learning (FSCL) network is used to achieve two-way division. To avoid over-split, merging condition is defined to merge the clusters that are close enough to each other at each layer. Experimental results show that HFSCL has the desired ability for CQ.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages786-789
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul
Duration: 2010 Aug 232010 Aug 26

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CityIstanbul
Period10/8/2310/8/26

Fingerprint

Color
Binary trees
Merging

Keywords

  • Color quantization(CQ)
  • Competitive learning
  • Tree structure

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Zhang, J., & Furuzuki, T. (2010). A hierarchical clustering method for color quantization. In Proceedings - International Conference on Pattern Recognition (pp. 786-789). [5596046] https://doi.org/10.1109/ICPR.2010.198

A hierarchical clustering method for color quantization. / Zhang, Jun; Furuzuki, Takayuki.

Proceedings - International Conference on Pattern Recognition. 2010. p. 786-789 5596046.

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

Zhang, J & Furuzuki, T 2010, A hierarchical clustering method for color quantization. in Proceedings - International Conference on Pattern Recognition., 5596046, pp. 786-789, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, 10/8/23. https://doi.org/10.1109/ICPR.2010.198
Zhang J, Furuzuki T. A hierarchical clustering method for color quantization. In Proceedings - International Conference on Pattern Recognition. 2010. p. 786-789. 5596046 https://doi.org/10.1109/ICPR.2010.198
Zhang, Jun ; Furuzuki, Takayuki. / A hierarchical clustering method for color quantization. Proceedings - International Conference on Pattern Recognition. 2010. pp. 786-789
@inproceedings{e8518e0277964d04bb5af87a6003b258,
title = "A hierarchical clustering method for color quantization",
abstract = "In this paper, we propose a hierarchical frequency sensitive competitive learning (HFSCL) method to achieve color quantization (CQ). In HFSCL, the appropriate number of quantized colors and the palette can be obtained by an adaptive procedure following a binary tree structure with nodes and layers. Starting from the root node that contains all colors in an image until all nodes are examined by split conditions, a binary tree will be generated. In each node of the tree, a frequency sensitive competitive learning (FSCL) network is used to achieve two-way division. To avoid over-split, merging condition is defined to merge the clusters that are close enough to each other at each layer. Experimental results show that HFSCL has the desired ability for CQ.",
keywords = "Color quantization(CQ), Competitive learning, Tree structure",
author = "Jun Zhang and Takayuki Furuzuki",
year = "2010",
doi = "10.1109/ICPR.2010.198",
language = "English",
isbn = "9780769541099",
pages = "786--789",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - A hierarchical clustering method for color quantization

AU - Zhang, Jun

AU - Furuzuki, Takayuki

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a hierarchical frequency sensitive competitive learning (HFSCL) method to achieve color quantization (CQ). In HFSCL, the appropriate number of quantized colors and the palette can be obtained by an adaptive procedure following a binary tree structure with nodes and layers. Starting from the root node that contains all colors in an image until all nodes are examined by split conditions, a binary tree will be generated. In each node of the tree, a frequency sensitive competitive learning (FSCL) network is used to achieve two-way division. To avoid over-split, merging condition is defined to merge the clusters that are close enough to each other at each layer. Experimental results show that HFSCL has the desired ability for CQ.

AB - In this paper, we propose a hierarchical frequency sensitive competitive learning (HFSCL) method to achieve color quantization (CQ). In HFSCL, the appropriate number of quantized colors and the palette can be obtained by an adaptive procedure following a binary tree structure with nodes and layers. Starting from the root node that contains all colors in an image until all nodes are examined by split conditions, a binary tree will be generated. In each node of the tree, a frequency sensitive competitive learning (FSCL) network is used to achieve two-way division. To avoid over-split, merging condition is defined to merge the clusters that are close enough to each other at each layer. Experimental results show that HFSCL has the desired ability for CQ.

KW - Color quantization(CQ)

KW - Competitive learning

KW - Tree structure

UR - http://www.scopus.com/inward/record.url?scp=78149475185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149475185&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.198

DO - 10.1109/ICPR.2010.198

M3 - Conference contribution

AN - SCOPUS:78149475185

SN - 9780769541099

SP - 786

EP - 789

BT - Proceedings - International Conference on Pattern Recognition

ER -