Object recognition with luminance, rotation and location invariance

Takami Satonaka*, Takaaki Baba, Tatsuo Otsuki, Takao Chikamura, Teresa H. Meng

*この研究の対応する著者

研究成果: Conference contribution

10 被引用数 (Scopus)

抄録

In this paper we propose a neural network based on image synthesis, histogram adaptive quantization and the discrete cosine transformation (DCT) for object recognition with luminance, rotation and location invariance. An efficient representation of the invariant features is constructed using a three-dimensional memory structure. The performance of luminance and rotation invariance is illustrated by reduced error rates in face recognition. The error rate of using two-dimensional DCT is improved from 13.6% to 2.4% with the aid of the proposed image synthesis procedure. The 2.4% error rate is better than all previously reported results using Karhunen-Loeve transform convolution networks and eigenface models. In using DCT, our approach also enjoys the additional advantage of greatly reduced computational complexity.

本文言語English
ホスト出版物のタイトルIEEE International Conference on Image Processing
Place of PublicationLos Alamitos, CA, United States
出版社IEEE Comp Soc
ページ336-339
ページ数4
3
出版ステータスPublished - 1997
外部発表はい
イベントProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA
継続期間: 1997 10 261997 10 29

Other

OtherProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3)
CitySanta Barbara, CA, USA
Period97/10/2697/10/29

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識
  • ハードウェアとアーキテクチャ
  • 電子工学および電気工学

フィンガープリント

「Object recognition with luminance, rotation and location invariance」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル