An automatic segmentation technique for color images based on SOFM neural network

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

3 Citations (Scopus)

Abstract

In this paper, an automatic segmentation method based on self-organizing feature map (SOFM) neural network (NN) is presented for color images. First, a binary tree clustering procedure is used to cluster the colors in an image. In each node of the tree, a SOFM NN is used as a classifier which is fed by image color values. The output neurons of the SOFM NN define the color classes for each node. In our method, the number of color classes for each node is two. For each node of the tree, Hotelling transform based splitting condition is used to define if the current color classes should be split. To speed up the entire algorithm, a nearest neighbor interpolation is used to get the small training set for SOFM NN. Once the colors in an image are clustered, it is easy to segment a target by analyzing the color feature in an image. The method is independent of the color scheme, so it is applicable to any type of color images. Our experimental results show the validity of the proposed method.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages3528-3533
Number of pages6
DOIs
Publication statusPublished - 2009
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA
Duration: 2009 Jun 142009 Jun 19

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
CityAtlanta, GA
Period09/6/1409/6/19

Fingerprint

Self organizing maps
Color
Neural networks
Binary trees
Neurons
Interpolation
Classifiers

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Zhang, J., & Furuzuki, T. (2009). An automatic segmentation technique for color images based on SOFM neural network. In Proceedings of the International Joint Conference on Neural Networks (pp. 3528-3533). [5178725] https://doi.org/10.1109/IJCNN.2009.5178725

An automatic segmentation technique for color images based on SOFM neural network. / Zhang, Jun; Furuzuki, Takayuki.

Proceedings of the International Joint Conference on Neural Networks. 2009. p. 3528-3533 5178725.

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

Zhang, J & Furuzuki, T 2009, An automatic segmentation technique for color images based on SOFM neural network. in Proceedings of the International Joint Conference on Neural Networks., 5178725, pp. 3528-3533, 2009 International Joint Conference on Neural Networks, IJCNN 2009, Atlanta, GA, 09/6/14. https://doi.org/10.1109/IJCNN.2009.5178725
Zhang J, Furuzuki T. An automatic segmentation technique for color images based on SOFM neural network. In Proceedings of the International Joint Conference on Neural Networks. 2009. p. 3528-3533. 5178725 https://doi.org/10.1109/IJCNN.2009.5178725
Zhang, Jun ; Furuzuki, Takayuki. / An automatic segmentation technique for color images based on SOFM neural network. Proceedings of the International Joint Conference on Neural Networks. 2009. pp. 3528-3533
@inproceedings{2a768b25433e4f8795317d00a8824e54,
title = "An automatic segmentation technique for color images based on SOFM neural network",
abstract = "In this paper, an automatic segmentation method based on self-organizing feature map (SOFM) neural network (NN) is presented for color images. First, a binary tree clustering procedure is used to cluster the colors in an image. In each node of the tree, a SOFM NN is used as a classifier which is fed by image color values. The output neurons of the SOFM NN define the color classes for each node. In our method, the number of color classes for each node is two. For each node of the tree, Hotelling transform based splitting condition is used to define if the current color classes should be split. To speed up the entire algorithm, a nearest neighbor interpolation is used to get the small training set for SOFM NN. Once the colors in an image are clustered, it is easy to segment a target by analyzing the color feature in an image. The method is independent of the color scheme, so it is applicable to any type of color images. Our experimental results show the validity of the proposed method.",
author = "Jun Zhang and Takayuki Furuzuki",
year = "2009",
doi = "10.1109/IJCNN.2009.5178725",
language = "English",
isbn = "9781424435531",
pages = "3528--3533",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - An automatic segmentation technique for color images based on SOFM neural network

AU - Zhang, Jun

AU - Furuzuki, Takayuki

PY - 2009

Y1 - 2009

N2 - In this paper, an automatic segmentation method based on self-organizing feature map (SOFM) neural network (NN) is presented for color images. First, a binary tree clustering procedure is used to cluster the colors in an image. In each node of the tree, a SOFM NN is used as a classifier which is fed by image color values. The output neurons of the SOFM NN define the color classes for each node. In our method, the number of color classes for each node is two. For each node of the tree, Hotelling transform based splitting condition is used to define if the current color classes should be split. To speed up the entire algorithm, a nearest neighbor interpolation is used to get the small training set for SOFM NN. Once the colors in an image are clustered, it is easy to segment a target by analyzing the color feature in an image. The method is independent of the color scheme, so it is applicable to any type of color images. Our experimental results show the validity of the proposed method.

AB - In this paper, an automatic segmentation method based on self-organizing feature map (SOFM) neural network (NN) is presented for color images. First, a binary tree clustering procedure is used to cluster the colors in an image. In each node of the tree, a SOFM NN is used as a classifier which is fed by image color values. The output neurons of the SOFM NN define the color classes for each node. In our method, the number of color classes for each node is two. For each node of the tree, Hotelling transform based splitting condition is used to define if the current color classes should be split. To speed up the entire algorithm, a nearest neighbor interpolation is used to get the small training set for SOFM NN. Once the colors in an image are clustered, it is easy to segment a target by analyzing the color feature in an image. The method is independent of the color scheme, so it is applicable to any type of color images. Our experimental results show the validity of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=70449405049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449405049&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2009.5178725

DO - 10.1109/IJCNN.2009.5178725

M3 - Conference contribution

AN - SCOPUS:70449405049

SN - 9781424435531

SP - 3528

EP - 3533

BT - Proceedings of the International Joint Conference on Neural Networks

ER -