圖像濾波的形態(tài)學開、閉型神經(jīng)網(wǎng)絡算法
MORPHOLOGICAL OPENING AND CLOSING NEURAL NETWORKS FOR IMAGE FILTERING
-
摘要: 該文設計完成了一種具有實用意義的形態(tài)學開、閉濾波的神經(jīng)網(wǎng)絡模型及其濾波參數(shù)的優(yōu)化訓練算法。實驗結(jié)果表明該方法設計簡便,實用性強且易于推廣,對提高形態(tài)濾波性能效果明顯。分析表明,形態(tài)濾波器可分解為形態(tài)濾波運算和結(jié)構元素選擇兩個基本問題。形態(tài)濾波運算規(guī)則已由定義本身確定,于是形態(tài)濾波器的最終濾波性能就僅僅取決于結(jié)構元素的選擇。進行自適應優(yōu)化訓練的目的正是使結(jié)構元素具有圖像目標的形態(tài)結(jié)構特征,從而使形態(tài)濾波器對復雜變化的圖像具有良好的濾波性能和穩(wěn)健的適應能力。Abstract: This paper presents morphological neural networks of opening and closing operation for pratical use, and the algorithm to design optimal parameters of a morphological filter, Experimental results show that this method is good in practice and easy to extend. It has better filtering properties than that of the conventional morphological ones. The task of creating a morphological filter can be divided into two basic problems, selecting a morphological operation and Structuring Element (SE). The set of morpholo...
-
E.R. Dougherty, et al., Digital Image Processing Methods, New York, Marcel Dekker, 1994,110-138.[2]龔煒,石青云,程民德,數(shù)字空間中的數(shù)學形態(tài)學,北京,科學出版社,1997,137-162.[3]C.P. Suarez-Araujo, Novel neural-network models for computing homothetic invariances: Animage algebra notation, J. Math. Imaging and Vision, 1997, 7(1), 69-83.[4]Yonggwan Won, et al., Morphological shared-weight networks with applications to automatictarget recognition, IEEE Trans. on Neural Networks, 1997, NN-8(5), 1195-1203.[5]Gerhard X. Ritter, Morphological associatiative memories, IEEE Trans. on Neural Networks,1998, NN-9(2), 281-292.[6]余農(nóng),李吉成,一種自適應訓練形態(tài)濾波參數(shù)的神經(jīng)網(wǎng)絡方法,中國電子學會第四屆青年學術年會文集,北京,電子工業(yè)出版社,1998,537-540.[7]李吉成,李飚,灰度形態(tài)濾波器的神經(jīng)網(wǎng)絡實現(xiàn)方法,系統(tǒng)工程與電子技術,1999,21(3),56-59.[8]汪云九,崔,齊翔林,BP學習網(wǎng)絡中權值的感受野型初始化研究,自然科學進展,1996,6(3),346-350. -
計量
- 文章訪問數(shù): 2368
- HTML全文瀏覽量: 129
- PDF下載量: 523
- 被引次數(shù): 0
下載:
