A neural network approach to color image classification

M. Shinmoto, Yasue Mitsukura, M. Fukumi, N. Akamatsu

研究成果: Conference contribution

抄録

The paper presents a method for image classification by neural networks which uses characteristic data extracted from images. In order to extract characteristic data, image pixels are divided by a clustering method on HSI 3-dimensional-color space and processed by labeling to select domains. The information extracted from the domains is characteristic data (color information, position information and area information) of the image. Another characteristic data, which is extracted by Hough transform, is added to the feature and a comparative experiment is conducted. Finally the validity of this technique is verified by means of computer simulation.

元の言語English
ホスト出版物のタイトルICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
出版者Institute of Electrical and Electronics Engineers Inc.
ページ675-679
ページ数5
2
ISBN(印刷物)9810475241, 9789810475246
DOI
出版物ステータスPublished - 2002
外部発表Yes
イベント9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
継続期間: 2002 11 182002 11 22

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
Singapore
Singapore
期間02/11/1802/11/22

Fingerprint

Image classification
Color
Neural networks
Hough transforms
Labeling
Pixels
Computer simulation
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

これを引用

Shinmoto, M., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2002). A neural network approach to color image classification. : ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (巻 2, pp. 675-679). [1198143] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1198143

A neural network approach to color image classification. / Shinmoto, M.; Mitsukura, Yasue; Fukumi, M.; Akamatsu, N.

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. 巻 2 Institute of Electrical and Electronics Engineers Inc., 2002. p. 675-679 1198143.

研究成果: Conference contribution

Shinmoto, M, Mitsukura, Y, Fukumi, M & Akamatsu, N 2002, A neural network approach to color image classification. : ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. 巻. 2, 1198143, Institute of Electrical and Electronics Engineers Inc., pp. 675-679, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 02/11/18. https://doi.org/10.1109/ICONIP.2002.1198143
Shinmoto M, Mitsukura Y, Fukumi M, Akamatsu N. A neural network approach to color image classification. : ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. 巻 2. Institute of Electrical and Electronics Engineers Inc. 2002. p. 675-679. 1198143 https://doi.org/10.1109/ICONIP.2002.1198143
Shinmoto, M. ; Mitsukura, Yasue ; Fukumi, M. ; Akamatsu, N. / A neural network approach to color image classification. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. 巻 2 Institute of Electrical and Electronics Engineers Inc., 2002. pp. 675-679
@inproceedings{b57c237ebbe34d07bec7d252fe3a7e42,
title = "A neural network approach to color image classification",
abstract = "The paper presents a method for image classification by neural networks which uses characteristic data extracted from images. In order to extract characteristic data, image pixels are divided by a clustering method on HSI 3-dimensional-color space and processed by labeling to select domains. The information extracted from the domains is characteristic data (color information, position information and area information) of the image. Another characteristic data, which is extracted by Hough transform, is added to the feature and a comparative experiment is conducted. Finally the validity of this technique is verified by means of computer simulation.",
author = "M. Shinmoto and Yasue Mitsukura and M. Fukumi and N. Akamatsu",
year = "2002",
doi = "10.1109/ICONIP.2002.1198143",
language = "English",
isbn = "9810475241",
volume = "2",
pages = "675--679",
booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A neural network approach to color image classification

AU - Shinmoto, M.

AU - Mitsukura, Yasue

AU - Fukumi, M.

AU - Akamatsu, N.

PY - 2002

Y1 - 2002

N2 - The paper presents a method for image classification by neural networks which uses characteristic data extracted from images. In order to extract characteristic data, image pixels are divided by a clustering method on HSI 3-dimensional-color space and processed by labeling to select domains. The information extracted from the domains is characteristic data (color information, position information and area information) of the image. Another characteristic data, which is extracted by Hough transform, is added to the feature and a comparative experiment is conducted. Finally the validity of this technique is verified by means of computer simulation.

AB - The paper presents a method for image classification by neural networks which uses characteristic data extracted from images. In order to extract characteristic data, image pixels are divided by a clustering method on HSI 3-dimensional-color space and processed by labeling to select domains. The information extracted from the domains is characteristic data (color information, position information and area information) of the image. Another characteristic data, which is extracted by Hough transform, is added to the feature and a comparative experiment is conducted. Finally the validity of this technique is verified by means of computer simulation.

UR - http://www.scopus.com/inward/record.url?scp=84964498712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964498712&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1198143

DO - 10.1109/ICONIP.2002.1198143

M3 - Conference contribution

AN - SCOPUS:84964498712

SN - 9810475241

SN - 9789810475246

VL - 2

SP - 675

EP - 679

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

PB - Institute of Electrical and Electronics Engineers Inc.

ER -