A neural network approach to color image classification

Masayuki Shinmoto, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

研究成果: Conference article

2 引用 (Scopus)

抜粋

This 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 YCrCb 3-dimensionl-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 Wavelet transform, is added to the feature and a comparative experiment is conducted. Finally the validity of this technique is verified by means of computer simulations.

元の言語English
ページ(範囲)617-622
ページ数6
ジャーナルLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
2773 PART 1
出版物ステータスPublished - 2003 12 1
外部発表Yes
イベント7th International Conference, KES 2003 - Oxford, United Kingdom
継続期間: 2003 9 32003 9 5

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

フィンガープリント A neural network approach to color image classification' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用