Neural net based image retrieval by using color and location information

Motomichi Inoue, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

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

3 Citations (Scopus)

Abstract

In this paper a neural net-based image retrieval method is presented, in which color and location features are extracted from images. This method can retrieve similar images to a selected one from a large data set of color images. In particular, the location features in the color distribution of an image are important in the image retrieval. This image retrieval method extracts color features and their location information included in an image. A neural network tries to find images with similar features from a data set. First, images are translated into gray-scale ones and then are divided into eight regions based on gray scale values. The color and location features are extracted from these regions after integration of regions. The RGB and HSV color values in each region, area, and X- and Y-values in the orthogonal coordinates are learned by the multi-layered neural network. After learning, the neural network evaluates the similarity between a selected image and the other ones in the data set. Similar images found by the neural network are retrieval results.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages2575-2579
Number of pages5
Volume4
Publication statusPublished - 2000
Externally publishedYes
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11

Other

Other2000 IEEE International Conference on Systems, Man and Cybernetics
CityNashville, TN, USA
Period00/10/800/10/11

Fingerprint

Image retrieval
Color
Neural networks

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Inoue, M., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2000). Neural net based image retrieval by using color and location information. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 4, pp. 2575-2579). IEEE.

Neural net based image retrieval by using color and location information. / Inoue, Motomichi; Mitsukura, Yasue; Fukumi, Minoru; Akamatsu, Norio.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 2000. p. 2575-2579.

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

Inoue, M, Mitsukura, Y, Fukumi, M & Akamatsu, N 2000, Neural net based image retrieval by using color and location information. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 4, IEEE, pp. 2575-2579, 2000 IEEE International Conference on Systems, Man and Cybernetics, Nashville, TN, USA, 00/10/8.
Inoue M, Mitsukura Y, Fukumi M, Akamatsu N. Neural net based image retrieval by using color and location information. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4. IEEE. 2000. p. 2575-2579
Inoue, Motomichi ; Mitsukura, Yasue ; Fukumi, Minoru ; Akamatsu, Norio. / Neural net based image retrieval by using color and location information. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 2000. pp. 2575-2579
@inproceedings{87b4da17ffc24c8781ad74a2aafe6a08,
title = "Neural net based image retrieval by using color and location information",
abstract = "In this paper a neural net-based image retrieval method is presented, in which color and location features are extracted from images. This method can retrieve similar images to a selected one from a large data set of color images. In particular, the location features in the color distribution of an image are important in the image retrieval. This image retrieval method extracts color features and their location information included in an image. A neural network tries to find images with similar features from a data set. First, images are translated into gray-scale ones and then are divided into eight regions based on gray scale values. The color and location features are extracted from these regions after integration of regions. The RGB and HSV color values in each region, area, and X- and Y-values in the orthogonal coordinates are learned by the multi-layered neural network. After learning, the neural network evaluates the similarity between a selected image and the other ones in the data set. Similar images found by the neural network are retrieval results.",
author = "Motomichi Inoue and Yasue Mitsukura and Minoru Fukumi and Norio Akamatsu",
year = "2000",
language = "English",
volume = "4",
pages = "2575--2579",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Neural net based image retrieval by using color and location information

AU - Inoue, Motomichi

AU - Mitsukura, Yasue

AU - Fukumi, Minoru

AU - Akamatsu, Norio

PY - 2000

Y1 - 2000

N2 - In this paper a neural net-based image retrieval method is presented, in which color and location features are extracted from images. This method can retrieve similar images to a selected one from a large data set of color images. In particular, the location features in the color distribution of an image are important in the image retrieval. This image retrieval method extracts color features and their location information included in an image. A neural network tries to find images with similar features from a data set. First, images are translated into gray-scale ones and then are divided into eight regions based on gray scale values. The color and location features are extracted from these regions after integration of regions. The RGB and HSV color values in each region, area, and X- and Y-values in the orthogonal coordinates are learned by the multi-layered neural network. After learning, the neural network evaluates the similarity between a selected image and the other ones in the data set. Similar images found by the neural network are retrieval results.

AB - In this paper a neural net-based image retrieval method is presented, in which color and location features are extracted from images. This method can retrieve similar images to a selected one from a large data set of color images. In particular, the location features in the color distribution of an image are important in the image retrieval. This image retrieval method extracts color features and their location information included in an image. A neural network tries to find images with similar features from a data set. First, images are translated into gray-scale ones and then are divided into eight regions based on gray scale values. The color and location features are extracted from these regions after integration of regions. The RGB and HSV color values in each region, area, and X- and Y-values in the orthogonal coordinates are learned by the multi-layered neural network. After learning, the neural network evaluates the similarity between a selected image and the other ones in the data set. Similar images found by the neural network are retrieval results.

UR - http://www.scopus.com/inward/record.url?scp=0034511067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034511067&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 2575

EP - 2579

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -