ニューラルネットワークによる位置ずれ・回転に不変なパターン認識システム

DOI Web Site Web Site 被引用文献1件

書誌事項

タイトル別名
  • Pattern Recognition System Insensitive to Translation and Rotation by Neural Network
  • ニューラル ネットワーク ニ ヨル イチズレ カイテン ニ フヘン ナ パター

この論文をさがす

抄録

In pattern recognition, we often deal with classification problems in which the retinal input patterns may be subject to translation, rotation, scale change, perspective change etc. Usual pattern recognition methods by statistical discrimination functions are not powerful to classify those patterns.<br>In this paper, a new approach for pattern recognition by a neural network is proposed based on the concept involving an invariance network and a descrambler network. The invariance network plays an important role in producing a set of outputs which are invariant to translation, and rotation, etc., of the retinal input pattern. The descrambler network is used to classify the scrambled data into the original patterns by using back-propagation algorithm. The structure of proposed neural networks is similar to that by Widrow, et al.<br>But the sigmoid functions are adopted as nonlinear elements in the neural networks while Widrow's MR II is based on signam functions. Hence, the back-propagation method can be used in the learning algorithm of descrambler network.<br>Finally, some numerical results are illustrated to show the effectiveness of the present algorithm for pattern recognition.

収録刊行物

被引用文献 (1)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ