[1]张 群,闵乐泉.灰度逻辑蕴含运算CNN模板的鲁棒性设计[J].南京理工大学学报(自然科学版),2014,38(04):490-495.
 Zhang Qun,Min Lequan.Robustness design of new templates for gray-scale logic converse implication operation CNN[J].Journal of Nanjing University of Science and Technology,2014,38(04):490-495.
点击复制

灰度逻辑蕴含运算CNN模板的鲁棒性设计
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
38卷
期数:
2014年04期
页码:
490-495
栏目:
出版日期:
2014-08-31

文章信息/Info

Title:
Robustness design of new templates for gray-scale logic converse implication operation CNN
作者:
张 群1闵乐泉12
北京科技大学 1.自动化学院; 2.数理学院,北京 100083
Author(s):
Zhang Qun1Min Lequan12
1.School of Automation and Electrical Engineering; 2.School of Mathematics and Physics, University of Science and Technology Beijing,Beijing 100083,China
关键词:
细胞神经网络 灰度图像 逻辑蕴含运算 鲁棒性设计 模板参数
Keywords:
cellular neural network gray-scale images logic converse implication operation template robustness design template parameter
分类号:
TP183
摘要:
为了解决灰度图像逻辑蕴含运算的问题,该文对一类灰度图像逻辑蕴含运算细胞神经网络(Gray-scale logic converse implication operation cellular neural network,GLCIO CNN)进行了研究。通过制定两幅灰度图像之间的逻辑蕴含运算,设计了一类GLCIO CNN。根据GLCIO CNN的局部规则,对其模板进行鲁棒性设计,提出相应的鲁棒性设计定理,并给出了科学合理的数学证明。只要细胞神经网络的模板参数满足定理中提出的参数不等式,细胞神经网络(CNN)就能够对两幅灰度图像执行逻辑蕴含运算。实验结果验证了GLCIO CNN的有效性及鲁棒性设计定理的可行性。
Abstract:
To solve the logical converse implication operation between two gray-scale images,a kind of gray-scale logic converse implication operation cellular neural network(GLCIO CNN)is studied here.According to the converse implication operation,the Local Rules of GLCIO CNN is proposed.A theorem is given to design the robustness of the templates of GLCIO CNN.The theorem is proved.The theorem provides parameter inequalities for selecting suitable template parameters of GLCIO CNN to implement the corresponding tasks.The numerical simulation examples verify the validity of GLCNIO CNN,and the methodology is efficient in practical applications for computer digital image processing.

参考文献/References:

[1] Chua L O,Yang L.Cellular neural networks:theory[J].IEEE Transactions on Circuits Systems,1988,35(10):1257-1290.
[2]Dudek P J.An asynchronous cellular logic network for trigger-wave image processing on fine-grain massively parallel arrays[J].IEEE Transactions on Circuits and Systems-Ⅱ:Analog and Digital Signal Processing,2006,53:354-358.
[3]Sebastian Sudheer K,Sabir M.Adaptive function projective synchronization of two-cell Quantum-CNN chaotic oscillators with uncertain parameters[J].Physics Letters A,2009,373(21):1847-1851.
[4]Arun P V,Katiyar S K.Cellular neural network-based hybrid approach toward automatic image registration[J].Journal of Applied Remote Sensing,2013,7:1-11.
[5]Goras L,Chua L O.Turing patterns in CNNs—part Ⅱ:equations and behaviours[J].IEEE Transactions on Circuits and Systems-Ⅰ,1995,42(10):612-626.
[6]Li Huaqing,Liao Xiaofeng,Li Chuandong,et al.Edge detection of noisy images based on cellular neural networks[J].Commun Nonlinear Sci Numer Simulat,2011,16:3746-3759.
[7]Min Lequn,Lei Ming,Dong Xisong.New templates of CNN extracting corners of objects in gray-scale images[J].Journal of University of Science and Technology Beijing,2003,10(3):73-75.
[8]Liu Jinzhu,Min Lequan.Design for CNN templates with performances of global connectivity detection[J].Communications in Theoretical Physics,2004,41(1):151-156.
[9]赵建业,王新,余道衡.基于Gibbs图像模型的细胞神经网络模板设计法[J].电子学报,2000,28(1):48-52.
Zhao Jianye,Wang Xin,Yu Daoheng.A template design method for cellular neural networks based on Gibbs image model[J].Chinese Journal of Electronics,2000,28(1):48-52.
[10]Li Chunguang,Xu Hongbing,Liao Xiaofeng,et al.Tabu search for CNN template learning[J].Neurocomputing,2003,51(4):475-479.
[11]Fasih A,Chedjou J C,Kyamakya K.Cellular neural network trainer and template optimization for advanced robot locomotion,based on genetic algorithm[A].Proceedings of the 15th International Conference on Mechatronics and Machine Vision in Practice[C].Auckland,New Zealand:IEEE Press,2008:317-322.
[12]Fornarelli G,Giaquinto A.Adaptive particle swarm optimization for CNN associative memories design[J].Neurocomputing,2009,72(16-18):3851-3862.
[13]Basturk A,Gunay E.Efficient edge detection in digital images using a cellular neural network optimized by differential evolution algorithm[J].Expert Systems with Applications,2009,36(2):2645-2650.
[14]Chua L O,Thiran P.An analytic method for designing simple cellular neural networks[J].IEEE Transactions on Circuits and Systems,1991,38(11):1332-1341.
[15]Deng Shaojiang,Tian Yuan,Hu Xipeng,et al.Application of new advanced CNN structure with adaptive thresholds to color edge detection[J].Commun Nonlinear Sci Numer Simulat,2012,17:1637-1648.
[16]Liu Jinzhu,Min Lequan.Robust design of bipolar wave cellular neural network with applications[J].International Journal of Modelling,Identification and Control,2010,11(1/2):99-106.
[17]沙莎,刘金珠,闵乐泉.复合4邻域圈提取CNN的鲁棒性设计[J].计算机工程与应用,2011,47(2):197-199.
Sha Sha,Liu Jinzhu,Min Lequan.Robust designs for compound 4 adjoining points circle detection[J].Computer Engineering and Application,2011,47(2):197-199.

备注/Memo

备注/Memo:
收稿日期:2013-10-31 修回日期:2014-03-13
基金项目:国家自然科学基金(61074192); 校冶金工程研究院基础理论研究
基金项目(yj2010-019); 高等学校博士科研专项基金(06108104)
作者简介:张群(1988-),女,博士生,主要研究方向:细胞神经网络的理论及其在图像处理中的应用,E-mail:zhangqun7835@163.com; 通讯作者:闵乐泉(1951-),男,教授,主要研究方向:细胞神经网络的鲁棒性设计,基于CNN的图像处理,复杂网络的混沌同步理论与应用,混沌加密,复杂系统建模,E-mail:minlequan@sina.com。
引文格式:张群,闵乐泉.灰度逻辑蕴含运算CNN模板的鲁棒性设计[J].南京理工大学学报,2014,38(4):490-495.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2014-08-31