基于细胞神经网络边缘检测的自适应研究
|
摘要
针对细胞神经网络(CNN)在边缘提取中简单自适应模板对灰度图像边缘不完整的问题,提出了对简单模板进行改进,将四分模板细化为六分模板的方法.首先均分简单模板中的判定范围,然后重新推导在不同范围中各个自适应模板的各项取值,再对图像处理中常用的灰度图像进行边缘提取并与简单自适应模板的结果进行比较.实验结果表明:改进的自适应模板相比较于简单的自适应模板可以提取出更完整、清晰的边缘.
In order to solve the problem of incomplete edge of gray image by simple adaptive template in edge extraction by cellular neural network(CNN), a method is proposed to improve the simple template and refine the four-part template into six-part template. Firstly, the judgment range of the simple template is divided evenly.Secondly, the values of each adaptive template in different ranges are derived again. Finally, the edge extraction of the gray image commonly used in image processing is carried out and the results of the simple adaptive template are compared. Experimental results show that the improved adaptive template can extract more complete and clear edges than the simple adaptive template.
In order to solve the problem of incomplete edge of gray image by simple adaptive template in edge extraction by cellular neural network(CNN), a method is proposed to improve the simple template and refine the four-part template into six-part template. Firstly, the judgment range of the simple template is divided evenly.Secondly, the values of each adaptive template in different ranges are derived again. Finally, the edge extraction of the gray image commonly used in image processing is carried out and the results of the simple adaptive template are compared. Experimental results show that the improved adaptive template can extract more complete and clear edges than the simple adaptive template.
引文
[1]Chua L O,Yang L.Cellular neural networks:theorys[J].IEEE Trans on CAS,1988,35(10):1 257-1 272.DOI:10.1109/31.7600.
[2]Omrani H,Tayyebi A,Pijanowski B.Integrating the multi-label land-use concept and cellular automata with the artificial neural network-based land transformation model:an integrated ML-CA-LTM modeling framework[J].Mapping Sciences&Remote Sensing,2017,54(3):283-304.
[3]田袁.基于细胞神经网络的图像边缘提取[D].重庆:重庆大学,2012.Tian Y.Image edge extraction based on cellular neural network[D].Chongqing:Chongqing University,2012.
[4]李长军,任幸福.具有S-分布时滞的中立型细胞神经网络的周期解的存在性[J].中国海洋大学学报:自然科学版,2016,46(5):138-144.LI C J,REN X H.Existence of periodic solutions for neutral cellular neural networks with S-distribution delay[J].Journal of Ocean University of China:Natural Science Edition,2016,46(5):138-144.
[5]姜庆玲.基于细胞神经网络鲁棒性的彩色图像边缘检测[J].图学学报,2013,34(1):22-30.DOI:10.3969/j.issn.2095-302X.2013.01.004.Jiang Q L.Color image edge detection based on cellular neural network robustness[J].Journal of Graphics,2013,34(1):22-30.
[6]王红红.多邻域细胞神经网络融合优化算法和线性矩阵不等式的边缘检测算法研究[D].银川:北方民族大学,2012.Wang H H.Multi-neighbour cell neural network fusion optimization algorithm and edge detection algorithm for linear matrix inequality[D].Yinchuan:Northern University for Nationalities,2012.
[7]张宪红,张春蕊.一种改进的细胞神经网络图像边缘提取方法[J].暨南大学学报:自然科学与医学版,2017,38(2):178-184.Zhang X H,Zhang C R.An improved cellular neural network image edge extraction method[J].Journal of Jinan University:Natural Science&Medicine Edition,2017,38(2):178-184.
[8]蒋爱平,梁舒,马爽.基于形态学和细胞神经网络的边缘检测方法[J].光电工程,2008(10):76-80.DOI:10.3969/j.issn.1003-501X.2008.10.015.Jiang A P,Liang S,Ma S.Edge detection method based on morphology and cellular neural network[J].Opto-Electronic Engineering,2008(10):76-80.
[9]贾真真.基于记忆元件的细胞神经网络研究[D].武汉:华中科技大学,2016.Jia Z Z.Study of cell neural network based on memory element[D].Wuhan:Huazhong University of Science and Technology,2016.
[10]汤敏.基于细胞神经网络的灰度图像边缘提取[J].计算机工程与设计,2010,31(10):2 276-2 279.Tang M.Edge extraction of grayscale images based on cellular neural network[J].Computer Engineering and Design,2010,31(10):2 276-2 279.
[11]王勇,朱光,王瑛.细胞神经网络与改进AES的超混沌图像加密方案[J].计算机工程与应用,2018,54(21):194-200.Wang Y,Zhu G,Wang Y.Cellular neural network and improved AES hyperchaotic image encryption scheme[J].Computer Engineering and Applications,2018,54(21):194-200.
[12]Deng S J,Tian Y,Hu X P,et al.Application of new advanced cnn structure with adaptive thresholds to color edge detection[J].Commun Nonlinear Sci Number Simulat,2012(17):1 637-1 648.
[13]Hajjej B,Boussaid B,Zouinkhi A,et al.Implementation of an unknown input observer based on Cellular Neural Network[C].International Conference on Advanced Systems and Electric Technologies,Hammamet,Tunisia.2017:140-145.
[14]蒲越,李国东,赵静.基于细胞神经网络混沌特性的音频加密技术应用[J].云南大学学报:自然科学版,2017,39(4):539-546.Pu Y,Li G D,Zhao J.Application of audio encryption technology based on chaotic characteristics of cellular neural networks[J].Journal of Yunnan University:Natural Science Edition,2017,39(4):539-546.
[15]Han M,Yang X,Jiang E.An extreme learning machine based on cellular automata of edge detection for remote sensing images[J].Neurocomputing,2016,198:27-34.
[16]李静文.含有马尔可夫跳跃参数的模糊细胞神经网络稳定性研究[D].大连:大连交通大学,2013.Li J W.Stability of Fuzzy cellular neural networks with Markov jump parameters[D].Dalian:Dalian Jiaotong University,2013.
[17]黄蕾.基于CNN的灰度图像边缘提取算法中模板参数的研究[J].计算机与现代化,2006(6):69-72.DOI:10.3969/j.issn.1006-2475.2006.06.023.Huang L.Research on template parameters in gray-scale image edge extraction algorithm based on CNN[J].Computer and Modernization,2006(6):69-72.
[18]杨婷,段书凯,王丽丹,等.基于改进忆阻细胞神经网络的彩色图像边缘提取[J].中国科学:信息科学,2017,47(7):863-877.Yang T,Duan S K,Wang L D,et al.Color image edge extraction based on improved memristive cell neural network[J].Science of China:Information Science,2017,47(7):863-877.
[19]Gazi O B,Belal M,Abdelgalil H.Edge detection in satellite image using cellular neural network[J].International Journal of Advanced Computer Science&Applications,2014,5(10).DOI:10.14569/IJACSA.2014.051010.
[20]Wang Z X,Li L.Image edge detection based on cellular neural network and particle swarm optimization[J].计算机科学与技术汇刊:中英文版,2014,3(1):1-8.Wang Z X,Li L.Image edge detection based on cellular neural network and particle swarm optimization[J].Chinese Journal of Computer Science and Technology:Chinese/English Edition,2014,3(1):1-8.
[21]Pan C,Naeemi A.A proposal for energy-efficient cellular neural network based on spintronic devices[J].IEEE Transactions on Nanotechnology,2016,15(5):820-827.DOI:10.1109/TNANO.2016.2598147.
[2]Omrani H,Tayyebi A,Pijanowski B.Integrating the multi-label land-use concept and cellular automata with the artificial neural network-based land transformation model:an integrated ML-CA-LTM modeling framework[J].Mapping Sciences&Remote Sensing,2017,54(3):283-304.
[3]田袁.基于细胞神经网络的图像边缘提取[D].重庆:重庆大学,2012.Tian Y.Image edge extraction based on cellular neural network[D].Chongqing:Chongqing University,2012.
[4]李长军,任幸福.具有S-分布时滞的中立型细胞神经网络的周期解的存在性[J].中国海洋大学学报:自然科学版,2016,46(5):138-144.LI C J,REN X H.Existence of periodic solutions for neutral cellular neural networks with S-distribution delay[J].Journal of Ocean University of China:Natural Science Edition,2016,46(5):138-144.
[5]姜庆玲.基于细胞神经网络鲁棒性的彩色图像边缘检测[J].图学学报,2013,34(1):22-30.DOI:10.3969/j.issn.2095-302X.2013.01.004.Jiang Q L.Color image edge detection based on cellular neural network robustness[J].Journal of Graphics,2013,34(1):22-30.
[6]王红红.多邻域细胞神经网络融合优化算法和线性矩阵不等式的边缘检测算法研究[D].银川:北方民族大学,2012.Wang H H.Multi-neighbour cell neural network fusion optimization algorithm and edge detection algorithm for linear matrix inequality[D].Yinchuan:Northern University for Nationalities,2012.
[7]张宪红,张春蕊.一种改进的细胞神经网络图像边缘提取方法[J].暨南大学学报:自然科学与医学版,2017,38(2):178-184.Zhang X H,Zhang C R.An improved cellular neural network image edge extraction method[J].Journal of Jinan University:Natural Science&Medicine Edition,2017,38(2):178-184.
[8]蒋爱平,梁舒,马爽.基于形态学和细胞神经网络的边缘检测方法[J].光电工程,2008(10):76-80.DOI:10.3969/j.issn.1003-501X.2008.10.015.Jiang A P,Liang S,Ma S.Edge detection method based on morphology and cellular neural network[J].Opto-Electronic Engineering,2008(10):76-80.
[9]贾真真.基于记忆元件的细胞神经网络研究[D].武汉:华中科技大学,2016.Jia Z Z.Study of cell neural network based on memory element[D].Wuhan:Huazhong University of Science and Technology,2016.
[10]汤敏.基于细胞神经网络的灰度图像边缘提取[J].计算机工程与设计,2010,31(10):2 276-2 279.Tang M.Edge extraction of grayscale images based on cellular neural network[J].Computer Engineering and Design,2010,31(10):2 276-2 279.
[11]王勇,朱光,王瑛.细胞神经网络与改进AES的超混沌图像加密方案[J].计算机工程与应用,2018,54(21):194-200.Wang Y,Zhu G,Wang Y.Cellular neural network and improved AES hyperchaotic image encryption scheme[J].Computer Engineering and Applications,2018,54(21):194-200.
[12]Deng S J,Tian Y,Hu X P,et al.Application of new advanced cnn structure with adaptive thresholds to color edge detection[J].Commun Nonlinear Sci Number Simulat,2012(17):1 637-1 648.
[13]Hajjej B,Boussaid B,Zouinkhi A,et al.Implementation of an unknown input observer based on Cellular Neural Network[C].International Conference on Advanced Systems and Electric Technologies,Hammamet,Tunisia.2017:140-145.
[14]蒲越,李国东,赵静.基于细胞神经网络混沌特性的音频加密技术应用[J].云南大学学报:自然科学版,2017,39(4):539-546.Pu Y,Li G D,Zhao J.Application of audio encryption technology based on chaotic characteristics of cellular neural networks[J].Journal of Yunnan University:Natural Science Edition,2017,39(4):539-546.
[15]Han M,Yang X,Jiang E.An extreme learning machine based on cellular automata of edge detection for remote sensing images[J].Neurocomputing,2016,198:27-34.
[16]李静文.含有马尔可夫跳跃参数的模糊细胞神经网络稳定性研究[D].大连:大连交通大学,2013.Li J W.Stability of Fuzzy cellular neural networks with Markov jump parameters[D].Dalian:Dalian Jiaotong University,2013.
[17]黄蕾.基于CNN的灰度图像边缘提取算法中模板参数的研究[J].计算机与现代化,2006(6):69-72.DOI:10.3969/j.issn.1006-2475.2006.06.023.Huang L.Research on template parameters in gray-scale image edge extraction algorithm based on CNN[J].Computer and Modernization,2006(6):69-72.
[18]杨婷,段书凯,王丽丹,等.基于改进忆阻细胞神经网络的彩色图像边缘提取[J].中国科学:信息科学,2017,47(7):863-877.Yang T,Duan S K,Wang L D,et al.Color image edge extraction based on improved memristive cell neural network[J].Science of China:Information Science,2017,47(7):863-877.
[19]Gazi O B,Belal M,Abdelgalil H.Edge detection in satellite image using cellular neural network[J].International Journal of Advanced Computer Science&Applications,2014,5(10).DOI:10.14569/IJACSA.2014.051010.
[20]Wang Z X,Li L.Image edge detection based on cellular neural network and particle swarm optimization[J].计算机科学与技术汇刊:中英文版,2014,3(1):1-8.Wang Z X,Li L.Image edge detection based on cellular neural network and particle swarm optimization[J].Chinese Journal of Computer Science and Technology:Chinese/English Edition,2014,3(1):1-8.
[21]Pan C,Naeemi A.A proposal for energy-efficient cellular neural network based on spintronic devices[J].IEEE Transactions on Nanotechnology,2016,15(5):820-827.DOI:10.1109/TNANO.2016.2598147.