基于神经网络和数学形态学的海杂波抑制处理技术的研究应用
|
摘要
海杂波信号具有很强的相关性,特别是体现在海尖峰效应当中,这种相关性造成了常规的基于海杂波功率谱的频域滤波方法对海杂波的抑制效果不理想。为了有效地抑制海杂波,本文回避了在常规方法中出现的海杂波相关性问题,提出了一种从图像处理的角度来抑制海杂波的方法。该方法先利用图像复原技术对由航海雷达得到的海浪图像进行图像复原,去除海浪图像中的噪声,得到海杂波图像,之后利用图像分割技术判断海杂波图像中是否含有目标,如果有目标存在,将其分离出来。
图像复原部分提出了基于神经网络和数学形态学的图像复原技术,既继承了神经网络的拟合性质和收敛性质,又应用一种新型的形态学变形虫结构元素克服了传统滤波方法的缺点,在保持图像边缘信息的前提下,有效地平滑了图像中的噪声。四种改进的图像复原技术被给出,分别为基于Hopfield神经网络和数学形态学的图像复原技术、基于小波神经网络和数学形态学的图像复原技术、基于暂态混沌神经网络和数学形态学的图像复原技术及基于细胞神经网络和数学形态学的图像复原技术。
图像分割部分提出了两种新的图像分割技术和两种改进的基于神经网络的图像分割技术,分别为基于中心灰度级信息矩阵法的图像分割技术、基于级间灰度级信息矩阵法的图像分割技术、基于Hopfield神经网络的图像分割技术及基于暂态混沌神经网络的图像分割技术。
为了验证从图像处理角度提出的海杂波抑制方法,本文应用由IPIX航海雷达采集的无目标和有目标的两组海浪图像数据进行仿真实验,并对实验的结果做了细致的比较和分析,证实本文方法能够有效抑制海杂波。
The signal of sea clutter has a very strong correlation, especially manifested in the effect of sea spike. This correlation makes the traditional method of frequency-domain filtering based on power spectrum of sea clutter have not a so good suppressive effect. In order to suppress the sea clutter effectively, a method to suppress the sea clutter from the aspect of image processing is presented, which avoids the problem of sea clutter correlation emerged in traditional method. This method first makes use of image restoration technology to restore the ocean wave image obtained by the marine radar, and filters the noise in this ocean wave image to obtain the sea clutter image. And then it takes advantage of image segmentation technology to judge whether there is target in the sea clutter image. If does, separate them.
The image restoration part presents image restoration technique based on neural networks and mathematical morphology. It inherits fitting character and convergence property of neural networks. Besides, it presents a new type of morphology amoeba structuring element to overcome the disadvantages of traditional filter methods and the noise of image has been smoothed effectively on the premise of keeping image edge information. Four types of improved image restoration technique are given, including one based on Hopfield neural network and mathematical morphology, one based on wavelet neural network and mathematical morphology, one based on transiently chaotic neural network and mathematical morphology, and one based on cellular neural network and mathematical morphology.
The image segmentation part presents two new types of image segmentation technique and two improved ones based on neural networks, including one based on gray level information matrix method, which is obtained by minimizing the sum of distance values that is from every within-class gray level to central gray level, one based on gray level information matrix method, which is obtained by minimizing the sum of distance values that is from one within-class gray level to another, one based on Hopfield neural network, and one based on transiently chaotic neural network.
In order to verify the method of sea clutter suppression presented from the angle of image processing, two groups of data that one group has a target and the other not, which is collected by the IPIX marine radar is used to conduct simulation experiment. The experiment results have been analyzed and compared carefully, which show this method can suppress sea clutter effectively.
图像复原部分提出了基于神经网络和数学形态学的图像复原技术,既继承了神经网络的拟合性质和收敛性质,又应用一种新型的形态学变形虫结构元素克服了传统滤波方法的缺点,在保持图像边缘信息的前提下,有效地平滑了图像中的噪声。四种改进的图像复原技术被给出,分别为基于Hopfield神经网络和数学形态学的图像复原技术、基于小波神经网络和数学形态学的图像复原技术、基于暂态混沌神经网络和数学形态学的图像复原技术及基于细胞神经网络和数学形态学的图像复原技术。
图像分割部分提出了两种新的图像分割技术和两种改进的基于神经网络的图像分割技术,分别为基于中心灰度级信息矩阵法的图像分割技术、基于级间灰度级信息矩阵法的图像分割技术、基于Hopfield神经网络的图像分割技术及基于暂态混沌神经网络的图像分割技术。
为了验证从图像处理角度提出的海杂波抑制方法,本文应用由IPIX航海雷达采集的无目标和有目标的两组海浪图像数据进行仿真实验,并对实验的结果做了细致的比较和分析,证实本文方法能够有效抑制海杂波。
The signal of sea clutter has a very strong correlation, especially manifested in the effect of sea spike. This correlation makes the traditional method of frequency-domain filtering based on power spectrum of sea clutter have not a so good suppressive effect. In order to suppress the sea clutter effectively, a method to suppress the sea clutter from the aspect of image processing is presented, which avoids the problem of sea clutter correlation emerged in traditional method. This method first makes use of image restoration technology to restore the ocean wave image obtained by the marine radar, and filters the noise in this ocean wave image to obtain the sea clutter image. And then it takes advantage of image segmentation technology to judge whether there is target in the sea clutter image. If does, separate them.
The image restoration part presents image restoration technique based on neural networks and mathematical morphology. It inherits fitting character and convergence property of neural networks. Besides, it presents a new type of morphology amoeba structuring element to overcome the disadvantages of traditional filter methods and the noise of image has been smoothed effectively on the premise of keeping image edge information. Four types of improved image restoration technique are given, including one based on Hopfield neural network and mathematical morphology, one based on wavelet neural network and mathematical morphology, one based on transiently chaotic neural network and mathematical morphology, and one based on cellular neural network and mathematical morphology.
The image segmentation part presents two new types of image segmentation technique and two improved ones based on neural networks, including one based on gray level information matrix method, which is obtained by minimizing the sum of distance values that is from every within-class gray level to central gray level, one based on gray level information matrix method, which is obtained by minimizing the sum of distance values that is from one within-class gray level to another, one based on Hopfield neural network, and one based on transiently chaotic neural network.
In order to verify the method of sea clutter suppression presented from the angle of image processing, two groups of data that one group has a target and the other not, which is collected by the IPIX marine radar is used to conduct simulation experiment. The experiment results have been analyzed and compared carefully, which show this method can suppress sea clutter effectively.
引文
[1]Simon Haykin, Sadasivan Puthusserypady.海杂波的混沌动态特性[M].祝明波译.第一版.国防工业出版社.2007,1：6-11页
[2]李强,张守宏,张焕颖,曹运合.高掠海角下基于Radon变换的海杂波抑制方法[J].电子与信息学报,2007,5,29(5)：1087-1091页
[3]Yi Xu, Wei Feng Feng, Jun Yan Hao, Hwang, H.K. Adaptive radar clutter suppression[J]. OCEANS, MTS/IEEE Conference and Exhibition,2001,5,2:762-768P
[4]Jingyao Liu, Huadong Meng, Hao Zhang, Xiqin Wang. Radar Sea Clutter Suppression and Target Indication with a Spatial Tracking Filter [J]. Tsinghua Science & Technology, 2010,4,15:228-234P
[5]Nan Xie, Henry Leung, Hing Chan, A Multiple-Model Prediction Approach for Sea Clutter Modeling[J]. Transaction on Geoscience and Remote Sensing,2003,6,41: 1491-1502P
[6]Helmken, H.H, Vanderhill, M.J. Very low grazing angle radar backscatter from the ocean surface[J]. Record of the IEEE 1990 International Radar Conference,1990,5:181-188P
[7]Henry Leung, Neville Dubash, Nan Xie. Detection of Small Objects in Clutter Using a Ga-RBF Neural Network[J]. Transactions on Aerospace and Electronic Systems,2002,1, 38:98-118P
[8]Jing Hu, Wenwen Tung, Jianbo Gao. Detection of Low Observable Targets Within Sea Clutter by Structure Function Based Multifractal Analysis [J]. IEEE Transactions on Antennas and Propagation,2006,1,54:136-143P
[9]Harm W. Melief, Harm Greidanus, Piet van Genderen, Peter Hoogeboom. Analysis of Sea Spikes in Radar Sea Clutter Data[J]. IEEE Transactions on Geoscience and Remote Sensing,2006,4,44(4):985-993P
[10]梅孝安.IPIX雷达海尖峰统计特性的研究[J].飞行器测控学报,2007,4,26(2)：19-23页
[11]郝艳玲,唐艳红,卢志忠.航海雷达测波系统中降雨观测资料的分析与处理[J].遥感技术与应用.2008,4,23(2)：125-129页
[12]唐艳红,郝燕玲,卢志忠.基于小波变换的航海雷达图像噪声抑制方法[J].遥感技术与 应用.2009,6,24(3)：370-373页
[13]高远,张扬.海杂波的K-分布建模与仿真[J].电子科技,2007,3,9：52-55页
[14]Ward K.D. Compound representation of high resolution sea clutter[J]. Electronics Letters, 1981,7,17(16):561-563P
[15]H.Leung, S.Haykin. Is there a radar clutter attractor? [J]. Applied Physics Letters,1990,2, 56(6):593-595P
[16]刘艳苹.一种海杂波背景下快速小目标的检测方法[J].舰船电子对抗,2008,6,31(3)：41-44页
[17]R H Khan. Ocean-clutter model for high-frequency radar[J]. IEEE Journal of Oceanic Engineering,1991,4,16(2):181-188P
[18]T.Thayaparan, S.Kennedy. Detection of a Maneuvering Air Target in Sea Clutter using Joint Time-Frequency Analysis Techniques [J]. IEE Proc. Radar Sonar and Nav ig.2004, 2,151(1):19-30P
[19]Rafaat H Khan. Ocean Clutter Suppression for an HF Groud Wave Radar[J]. IEEE Journal of Oceanic Engineering,1997,5,2:512-515P
[20]J.Xie, Y.Yuan, Y.Liu. Suppression of sea clutter with orthogonal weighting for target detection in shipborne HFSWR[J]. IEEE Proc. Radar Sonar and Navig.2002,2,149(1): 39-44P
[21]J Xie, Y Liu. Experimental analysis of sea clutter in s hipborne HFSWR[J]. IEE Pro c. Radar, Sonar and Navig.2001,4,148(2):67-71P
[22]陈多芳,陈伯孝,秦国栋.岸-舰双基地波超视距雷达图像域海杂波抑制方法[J].电子学报,2010,2,38(2)：387-392页
[23]刘新骥,吴桂生,谭培勇.X-波段导航雷达海浪图像谱分析[J].信息与电子工程,2007,12,5(6)：405-408页
[24]唐艳红,郝燕玲,卢志忠.X波段航海雷达图像噪声检测与滤除方法研究[J].国土资源遥感,2008,6,76(2)：14-17页
[25]C Juarez, V. Ponomaryov, J.L. Sanchez. Implementation of Artificial Neural Networks for Recognition of Target and Clutter Images[J].2005 2nd International Conference on Electrical and Electronics Engineering, Mexico City,2005,9:64-67P
[26]Marcelo, G. S. Bruno, Jose M. F. Moura. Integration of Bayes Detection and Target Tracking in Real Clutter Image Sequences [J]. Radar Conference, Proceeding of the 2001 IEEE, Atlanta, GA, USA.2001,5,12:234-238P
[27]於建生,马红星,朱征宇.基于雷达回波相关特征的海杂波抑制方法[J].船舰电子工程.2009,6,29(6)：121-123页
[28]刘刚.MATLAB数字图像处理[M].第一版.机械工业出版社.2010,7：173-176页
[29]王艳华,刘伟宁,陈爱华.基于数学形态学变形虫的自适应图像滤波[J].激光与红外.2008,12,38(12)：1258-1261页
[30]Lerallut R, Goehm M, Decenciere E, Meyer, F. Noise reduction in 3D images using morphological amoebas[J]. IEEE International Conference on Image Processing, Genoa, Italy,2005,11:109-112P
[31]吴微.神经网络计算[M].第一版.高等教育出版社.2003,7：19-34页
[32]钟守铭,刘毕森,王晓梅,范小明.神经网络稳定性理论[M].第一版.科学出版社.2008,6：63-139页
[33]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].第三版.电子工业出版社.2007,9：133-150页
[34]Baoyun Wang, Jingnan Nie, Zhenya He. A transiently chaotic neural network implementation of the CDMA multi-user detector[J]. IEEE Transactions on Neural Networks,1999,9,10:1257-1259P
[35]Ikeguchi.T, Aihara.K. Associative dynamics in chaotic neural network[J]. Neural Networks.1997,8,3:83-89P
[36]Guoguang He, Luonan Chen, Kazuyuki Aihara. Associative memory with a controlled chaotic neural network[J]. Neurocomputing,2008,8,71(13):2794-2805P
[37]Zhang Jun, Gilbert G.Walter, et al. Wavelet Neural Networks for Function Learning[J]. IEEE Transaction on Signal Processing,1995,6,43(6):1485-1497P
[38]黄立宏李雪梅.细胞神经网络动力学[M].第一版.科学出版社.2007,4：1-38页
[39]Chua, L.O, Yang, L. Cellular neural networks:Theory[J]. IEEE Transactions on Circuits System,1988,10,35(10):1257-1272P
[40]Chua, L.O, Yang, L, Cellular neural networks:Application[J] IEEE Transactions on Circuits System,1988,10,35(10):1273-1290P
[41]Yew Kun Chee, Yeng Chai Soh. A robust Kalman Filter design for image restoration [J]. IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, UT,2001,5,3:1825-1828P
[42]A.Chan, J.Meloche. Image restoration[J], Journal of Statistical Planning and Inference, 1997,12,65(2):233-254P
[43]陈金林,韩志斌.一种图像复原算法的改进[J].应用数学,2007,11,20：151-154页
[44]Y.P. Guo, H.P. Lee, C.L. Teo. Multichannel image restorations using an iterative algorithm in space domain[J]. Image and Vision Computing,1996,6,14(6):389-400P
[45]Zhou, Y.T. Chellappa, R. Vaid, A. Jenkins, B.K. Image restoration using a neural network[J]. IEEE Transactions on Acoustics, Speech and Signal Processing,1988,7, 36(7):1141-1151P
[46]Joon K. Paik, Aggelos K. Katsaggelos. Image Restoration Using a Modified Hopfield Network[J]. Transactions on Image Processing,1992,1,1(1):49-63P
[47]Stuart W. Perry, Ling Guan. A partitioned modified Hopfield neural network algorithm for real-time image restoration[J]. Real-Time Imaging,1996,8,2:215-224P
[48]韩玉兵,吴乐南.基于状态连续变化的Hopfield神经网络的图像复原[J].信号处理,Signal Processing,2004,5,20(5)：431-435页
[49]仲伟波,金声震,宁书年.一种改进的Hopfield神经网络SST图像恢复方法[J].计算机工程,2004,12,30(24)：10-12页
[50]Dianhui Wang, Dillion, T. Chang, E. Pattern learning based image restoration using neural networks [J]. International Joint Conference on Neural Networks, Honolulu, Hawaii,2002,5,2(18):1481-1486P
[51]Leipo Yan, Lipo Wang. Applications of transiently chaotic neural networks to image restoration[J]., Proceedings of the 2003 International Conference on Neural Networks and Signal Processing, Nanjing, China,2003,12,1:265-269P
[52]Leipo Yan,Lip Wang, Kim-Hui Yap. A noisy chaotic neural network approach to image denoising[J].2004 International Conference on Image Processing, Singapore,2004,10,2: 1229-1232P
[53]曹学光,易沫.小波域边缘保持规整化图像复原[J].中国图像图形学报,2006,2,11(2)：224-229页
[54]Wei Qian, Clarke, L.P. Wavelet-based neural network with fuzzy-logic adaptivity for nuclear image restoration [J]. Proceedings of the IEEE,1996,10,84(10):1458-1473P
[55]冯强,于盛林,张维.基于细胞神经网络的图像复原新方法[J].中国图像图形学报,2009,3,14(3)：430-434页
[56]Celebi M.E, Guzelis C. Efficient image restoration using cellular neural networks [J]. Acoustics, Speech and Signal Processing,1997,4,4:3409-3412P
[57]Celebi M.E, Guzelis C. Image restoration using cellular neural network [J]. Electronics Letters,1997,1,33(7):43-45P
[58]张孟君,舒红,刘艳,王涛.基于空间曲面拟合的自适应阈值选取方法[J].武汉大学学报,2006,5,31(5)：395-397页
[59]Jun Tan. A Color Image Segmentation algorithm Based on Region Growing[J].2010 second international Conference on Computer Engineering and Technology, Chengdu, China,2010,6:634-637P
[60]A novel image segmentation method based on random walk[J]. Asia-Pacific Conference on Computational Intelligence and Industrial Applications, Wuhan, China,2009,11,1: 207-210P
[61]Bir Bhanu, Jing Peng. Adaptive Integrated Image Segmentation and Object Recognition [J]. IEEE Transactions on Systems, Man, and Cybernetics-part C:Applications and Reviews,2000,11,30(4):427-441P
[62]沈定刚,戚飞虎.基于神经网络的自适应图像分割[J].上海交通大学学报,1994,9,28：39-45页
[2]李强,张守宏,张焕颖,曹运合.高掠海角下基于Radon变换的海杂波抑制方法[J].电子与信息学报,2007,5,29(5)：1087-1091页
[3]Yi Xu, Wei Feng Feng, Jun Yan Hao, Hwang, H.K. Adaptive radar clutter suppression[J]. OCEANS, MTS/IEEE Conference and Exhibition,2001,5,2:762-768P
[4]Jingyao Liu, Huadong Meng, Hao Zhang, Xiqin Wang. Radar Sea Clutter Suppression and Target Indication with a Spatial Tracking Filter [J]. Tsinghua Science & Technology, 2010,4,15:228-234P
[5]Nan Xie, Henry Leung, Hing Chan, A Multiple-Model Prediction Approach for Sea Clutter Modeling[J]. Transaction on Geoscience and Remote Sensing,2003,6,41: 1491-1502P
[6]Helmken, H.H, Vanderhill, M.J. Very low grazing angle radar backscatter from the ocean surface[J]. Record of the IEEE 1990 International Radar Conference,1990,5:181-188P
[7]Henry Leung, Neville Dubash, Nan Xie. Detection of Small Objects in Clutter Using a Ga-RBF Neural Network[J]. Transactions on Aerospace and Electronic Systems,2002,1, 38:98-118P
[8]Jing Hu, Wenwen Tung, Jianbo Gao. Detection of Low Observable Targets Within Sea Clutter by Structure Function Based Multifractal Analysis [J]. IEEE Transactions on Antennas and Propagation,2006,1,54:136-143P
[9]Harm W. Melief, Harm Greidanus, Piet van Genderen, Peter Hoogeboom. Analysis of Sea Spikes in Radar Sea Clutter Data[J]. IEEE Transactions on Geoscience and Remote Sensing,2006,4,44(4):985-993P
[10]梅孝安.IPIX雷达海尖峰统计特性的研究[J].飞行器测控学报,2007,4,26(2)：19-23页
[11]郝艳玲,唐艳红,卢志忠.航海雷达测波系统中降雨观测资料的分析与处理[J].遥感技术与应用.2008,4,23(2)：125-129页
[12]唐艳红,郝燕玲,卢志忠.基于小波变换的航海雷达图像噪声抑制方法[J].遥感技术与 应用.2009,6,24(3)：370-373页
[13]高远,张扬.海杂波的K-分布建模与仿真[J].电子科技,2007,3,9：52-55页
[14]Ward K.D. Compound representation of high resolution sea clutter[J]. Electronics Letters, 1981,7,17(16):561-563P
[15]H.Leung, S.Haykin. Is there a radar clutter attractor? [J]. Applied Physics Letters,1990,2, 56(6):593-595P
[16]刘艳苹.一种海杂波背景下快速小目标的检测方法[J].舰船电子对抗,2008,6,31(3)：41-44页
[17]R H Khan. Ocean-clutter model for high-frequency radar[J]. IEEE Journal of Oceanic Engineering,1991,4,16(2):181-188P
[18]T.Thayaparan, S.Kennedy. Detection of a Maneuvering Air Target in Sea Clutter using Joint Time-Frequency Analysis Techniques [J]. IEE Proc. Radar Sonar and Nav ig.2004, 2,151(1):19-30P
[19]Rafaat H Khan. Ocean Clutter Suppression for an HF Groud Wave Radar[J]. IEEE Journal of Oceanic Engineering,1997,5,2:512-515P
[20]J.Xie, Y.Yuan, Y.Liu. Suppression of sea clutter with orthogonal weighting for target detection in shipborne HFSWR[J]. IEEE Proc. Radar Sonar and Navig.2002,2,149(1): 39-44P
[21]J Xie, Y Liu. Experimental analysis of sea clutter in s hipborne HFSWR[J]. IEE Pro c. Radar, Sonar and Navig.2001,4,148(2):67-71P
[22]陈多芳,陈伯孝,秦国栋.岸-舰双基地波超视距雷达图像域海杂波抑制方法[J].电子学报,2010,2,38(2)：387-392页
[23]刘新骥,吴桂生,谭培勇.X-波段导航雷达海浪图像谱分析[J].信息与电子工程,2007,12,5(6)：405-408页
[24]唐艳红,郝燕玲,卢志忠.X波段航海雷达图像噪声检测与滤除方法研究[J].国土资源遥感,2008,6,76(2)：14-17页
[25]C Juarez, V. Ponomaryov, J.L. Sanchez. Implementation of Artificial Neural Networks for Recognition of Target and Clutter Images[J].2005 2nd International Conference on Electrical and Electronics Engineering, Mexico City,2005,9:64-67P
[26]Marcelo, G. S. Bruno, Jose M. F. Moura. Integration of Bayes Detection and Target Tracking in Real Clutter Image Sequences [J]. Radar Conference, Proceeding of the 2001 IEEE, Atlanta, GA, USA.2001,5,12:234-238P
[27]於建生,马红星,朱征宇.基于雷达回波相关特征的海杂波抑制方法[J].船舰电子工程.2009,6,29(6)：121-123页
[28]刘刚.MATLAB数字图像处理[M].第一版.机械工业出版社.2010,7：173-176页
[29]王艳华,刘伟宁,陈爱华.基于数学形态学变形虫的自适应图像滤波[J].激光与红外.2008,12,38(12)：1258-1261页
[30]Lerallut R, Goehm M, Decenciere E, Meyer, F. Noise reduction in 3D images using morphological amoebas[J]. IEEE International Conference on Image Processing, Genoa, Italy,2005,11:109-112P
[31]吴微.神经网络计算[M].第一版.高等教育出版社.2003,7：19-34页
[32]钟守铭,刘毕森,王晓梅,范小明.神经网络稳定性理论[M].第一版.科学出版社.2008,6：63-139页
[33]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].第三版.电子工业出版社.2007,9：133-150页
[34]Baoyun Wang, Jingnan Nie, Zhenya He. A transiently chaotic neural network implementation of the CDMA multi-user detector[J]. IEEE Transactions on Neural Networks,1999,9,10:1257-1259P
[35]Ikeguchi.T, Aihara.K. Associative dynamics in chaotic neural network[J]. Neural Networks.1997,8,3:83-89P
[36]Guoguang He, Luonan Chen, Kazuyuki Aihara. Associative memory with a controlled chaotic neural network[J]. Neurocomputing,2008,8,71(13):2794-2805P
[37]Zhang Jun, Gilbert G.Walter, et al. Wavelet Neural Networks for Function Learning[J]. IEEE Transaction on Signal Processing,1995,6,43(6):1485-1497P
[38]黄立宏李雪梅.细胞神经网络动力学[M].第一版.科学出版社.2007,4：1-38页
[39]Chua, L.O, Yang, L. Cellular neural networks:Theory[J]. IEEE Transactions on Circuits System,1988,10,35(10):1257-1272P
[40]Chua, L.O, Yang, L, Cellular neural networks:Application[J] IEEE Transactions on Circuits System,1988,10,35(10):1273-1290P
[41]Yew Kun Chee, Yeng Chai Soh. A robust Kalman Filter design for image restoration [J]. IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, UT,2001,5,3:1825-1828P
[42]A.Chan, J.Meloche. Image restoration[J], Journal of Statistical Planning and Inference, 1997,12,65(2):233-254P
[43]陈金林,韩志斌.一种图像复原算法的改进[J].应用数学,2007,11,20：151-154页
[44]Y.P. Guo, H.P. Lee, C.L. Teo. Multichannel image restorations using an iterative algorithm in space domain[J]. Image and Vision Computing,1996,6,14(6):389-400P
[45]Zhou, Y.T. Chellappa, R. Vaid, A. Jenkins, B.K. Image restoration using a neural network[J]. IEEE Transactions on Acoustics, Speech and Signal Processing,1988,7, 36(7):1141-1151P
[46]Joon K. Paik, Aggelos K. Katsaggelos. Image Restoration Using a Modified Hopfield Network[J]. Transactions on Image Processing,1992,1,1(1):49-63P
[47]Stuart W. Perry, Ling Guan. A partitioned modified Hopfield neural network algorithm for real-time image restoration[J]. Real-Time Imaging,1996,8,2:215-224P
[48]韩玉兵,吴乐南.基于状态连续变化的Hopfield神经网络的图像复原[J].信号处理,Signal Processing,2004,5,20(5)：431-435页
[49]仲伟波,金声震,宁书年.一种改进的Hopfield神经网络SST图像恢复方法[J].计算机工程,2004,12,30(24)：10-12页
[50]Dianhui Wang, Dillion, T. Chang, E. Pattern learning based image restoration using neural networks [J]. International Joint Conference on Neural Networks, Honolulu, Hawaii,2002,5,2(18):1481-1486P
[51]Leipo Yan, Lipo Wang. Applications of transiently chaotic neural networks to image restoration[J]., Proceedings of the 2003 International Conference on Neural Networks and Signal Processing, Nanjing, China,2003,12,1:265-269P
[52]Leipo Yan,Lip Wang, Kim-Hui Yap. A noisy chaotic neural network approach to image denoising[J].2004 International Conference on Image Processing, Singapore,2004,10,2: 1229-1232P
[53]曹学光,易沫.小波域边缘保持规整化图像复原[J].中国图像图形学报,2006,2,11(2)：224-229页
[54]Wei Qian, Clarke, L.P. Wavelet-based neural network with fuzzy-logic adaptivity for nuclear image restoration [J]. Proceedings of the IEEE,1996,10,84(10):1458-1473P
[55]冯强,于盛林,张维.基于细胞神经网络的图像复原新方法[J].中国图像图形学报,2009,3,14(3)：430-434页
[56]Celebi M.E, Guzelis C. Efficient image restoration using cellular neural networks [J]. Acoustics, Speech and Signal Processing,1997,4,4:3409-3412P
[57]Celebi M.E, Guzelis C. Image restoration using cellular neural network [J]. Electronics Letters,1997,1,33(7):43-45P
[58]张孟君,舒红,刘艳,王涛.基于空间曲面拟合的自适应阈值选取方法[J].武汉大学学报,2006,5,31(5)：395-397页
[59]Jun Tan. A Color Image Segmentation algorithm Based on Region Growing[J].2010 second international Conference on Computer Engineering and Technology, Chengdu, China,2010,6:634-637P
[60]A novel image segmentation method based on random walk[J]. Asia-Pacific Conference on Computational Intelligence and Industrial Applications, Wuhan, China,2009,11,1: 207-210P
[61]Bir Bhanu, Jing Peng. Adaptive Integrated Image Segmentation and Object Recognition [J]. IEEE Transactions on Systems, Man, and Cybernetics-part C:Applications and Reviews,2000,11,30(4):427-441P
[62]沈定刚,戚飞虎.基于神经网络的自适应图像分割[J].上海交通大学学报,1994,9,28：39-45页