一种新的细胞神经网络阴影检测器的研究

汪海明; 郭仕德; 余道衡

一种新的细胞神经网络阴影检测器的研究

汪海明^{①;郭仕德},
郭仕德,
余道衡

计量
- 文章访问数: 2204
- HTML全文浏览量: 110
- PDF下载量: 560
- 被引次数: 0
出版历程
- 收稿日期: 2002-06-24
- 修回日期: 2002-11-14
- 刊出日期: 2003-11-19

A new kind of shadow detector based on cnn-ubn

Wang Haiming^{①;郭仕德},
Guo Shide,
Yu Daoheng

摘要

摘要: 该文深入研究了一种新的二维细胞自动机(CA),找到了几种新的算法规则可以用来实现字符的粗化处理和阴影检测,并且用这些规则设计了几种新的细胞神经网络,文中详细介绍了这些算法规则的布尔代数表达式和细胞神经网络学习算法。仿真结果证明了这种新的细胞神经网络是简单而有效的,同时也证明了可以用 CA规则来设计新的细胞神经网络,为细胞神经网络的设计找到了一种新颖有效的方法。
- 细胞神经网络（CNN）; 细胞自动机（CA）; 阴影检测器; 复值权重
Abstract: In this paper, a new kind of two-dimensional Cellular Automata (CA) is studied. Several algorithmic rules are discovered that can be used to design new Cellular Neural Networks (CNN) which can implement shadow detector and overstriking for character recognition. Their Boolean expressions and learning algorithms are introduced detailedly. The results of computer simulation confirm that this new approach is simpler and more effective than that given in the literature. Furthermore, these results also confirm that new CNN can be designed with CA rules and find a novel method to design CNN.

HTML全文

参考文献(1)

L.O. Chua, L. Yang, Cellular Neural Networks: Theory, IEEE Trans. on CAS, 1988, 35(10),1257-1272.[2]L.O. Chua, L. Yang, Cellular Neural Networks: Applications, IEEE Trans. on CAS, 1988, 35(10),1273-1290.[3]T. Kozek, T. Roska, A double time-scale CNN for solving two-dimensional Navier-Stokes equations, International Journal of Circuit Theory and Applications, 1996, 24(1), 49-55.[4]P.L. Venetianer, F. Werblin, T. Roska, Analogic CNN algorithms for some image compression and restoration tasks. IEEE Trans. on CAS-I, 1995, 42(5), 278-284.[5]C. Rekeczky, CNN architectures for constrained diffusion based locally adaptive image processing,International Journal of Circuit Theory and Applications 2002, 30(2/3): 287-312.[6]Jianye Zhao, Daoheng Yu, A new approach for ME multilevel image restoration based on CNN,International Journal of Circuit Theory and Applications, 1999, 27(3), 339-346.[7]Jianye Zhao, Haiming Wang, Daoheng Yu, A new approach for edge detection of noisy image based on CNN, International Journal of Circuit Theory and Applications, 2003, 31(2), 119-131.[8]S. Wolfman, Theory and Applications of Cellular Automata. Singapore, World Scientific Publishing, 1986 (Including all selected papers 1983-1986).[9]H. Masahiko, T. Aoki, H. Morimitsu, T. Higuchi, Implementation of reaction-diffusion cellular automata, IEEE Trans. on Circuits and Systems I: Fundamental Theory and Applications, 2002,49(1), 10-16.[10]P. Dasgupta, S. Chattopadhyay, P.P. Chaudhuri, I. Sengupta, Cellular automata-based recursive pseudoexhaustive test pattern generator. IEEE Trans. on Computers, 2001, 50(2), 177-185.[11]L.O. Chua, B.Shi, Exploiting Cellular Automata in the Design of Cellular Neural Networks for Binary Image Processing, ERL memo UCB/ERL M89/130, University of California, Berkeley,Nov. 15 , 1989.[12]T. Matsumoto, L. O. Chua, H. Suzuki, CNN cloning template: shadow detector, IEEE Trans. on CAS, 1990, 37(8), 1070-1073.[13]N.N. Aizenberg, I. N. Aizenberg, CNN-like networks based on multi-valued and universal binary neurons: learning and application to image processing, Cellular Neural Networks and their Applications, 1994. CNNA-94. Proceedings of the Third IEEE International Workshop on, Rome,Italy, 1994, 153-158.

施引文献

资源附件(0)

访问统计