利用模糊類神經網路於有旋轉平移及放大縮小不變性圖形識別

Abstract

本論文的主題是在探討如何應用模糊類神經網路於有旋轉，平移，放大及 縮小不變的圖形識別。我們所提出的識別系統包括兩個部份: 前處理器以 及模糊神經元分類器。在論文中，前處理器利用一些簡單的數學技巧，將 輸入圖形轉換為正規化圖形。其次，吾人將一些正規化圖形視為原型圖形 ，藉由這些原型圖形，我們可獲得相對應的歸屬函數。而模糊神經元分類 器將運用這些歸屬函數當作網路上的權重值。在訓練方面，我們採用單層 傾斜下降學習法則來訓練這些歸屬函數，也就是訓練網路的權重值。吾人 提供了一些模擬的例子來說明所提出的架構的可行性。 A hybrid pattern recognition system is described in this study which can recognize patterns with translation, rotation, scaling, and a combination of them. The system consists of two parts, i.e., the preprocessor and the fuzzy neuron classifier. The preprocessor, implemented by simple mapping techniques, generates the normalized input image. Next, the fuzzy neuron classifier associates the normalized input patterns with prototype patterns by making an optimal match of the weighted grade membership functions. A single layer gradient type algorithm is used to adapt the membership functions to the patterns to be recognized. Some numerical examples are provided to demonstrate the performance of the proposed technique.