Neural Pattern Recognition System Invariant to Rotation of Input Pattern and Its Application to Coin Recognition
-
- FUKUMI Minoru
- Faculty of Engineering, University of Tokushima
-
- OMATU Sigeru
- Faculty of Engineering, University of Tokushima
-
- TAKEDA Fumiaki
- GLORY Ltd
-
- KOSAKA Toshihisa
- GLORY Ltd
Bibliographic Information
- Other Title
-
- パターンの回転に対して不変なニューラルパターン認識システムとそのコイン認識への応用
- パターン ノ カイテン ニ タイシテ フヘン ナ パターン ニンシキ システム
Search this article
Description
We have already presented a pattern recognition system insensitive to translation and rotation by 90° using neural networks. In this paper, we propose a pattern recognition system invariant to rotation of input pattern by any number of degrees. The system consists of a fixed invariance net with many slabs and a trainable multi-layered network. To illustrate the effectiveness of the system, we apply it to a variable rotation coin recognition problem between 500 yen and 500 won coins.
Journal
-
- Transactions of the Institute of Systems, Control and Information Engineers
-
Transactions of the Institute of Systems, Control and Information Engineers 5 (1), 9-17, 1992
THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001205165867008
-
- NII Article ID
- 10007399047
-
- NII Book ID
- AN1013280X
-
- ISSN
- 2185811X
- 13425668
-
- NDL BIB ID
- 3751776
-
- Data Source
-
- JaLC
- NDL Search
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed