PCNN混沌特性与硬件实现研究
|
摘要
脉冲耦合神经网络(Pulse Coupled Neural Network, PCNN)是一种新型神经网络,是依据猫大脑视觉皮层神经细胞的同步脉冲发放现象提出的,是一种更接近生物视觉特性的神经网络模型,具有相似神经元同步点火特性,其应用受到广泛关注。作为非线性动力学系统,PCNN混沌特性研究的相关文献较少。目前大量文献关注PCNN模型的仿真实现研究,而对于基于硬件平台的PCNN算法实现仍是发展中的热点,是近年来文献关注的焦点。
本论文主要进行PCNN混沌特性研究和PCNN最大熵分割算法的FPGA硬件实现研究。具体如下：
1.通过对PCNN单个神经元模型的参数选取及非线性特性分析,分析了PCNN产生混沌特性的模型。对混沌模型如何稳定控制到期望点及对参考信号的跟踪方法进行了研究,实验结果表明,PCNN能产生混沌现象,且能按照期望点进行稳定控制,并能对参考信号进行很好地跟踪。
2.结合PCNN在图像分割方面的优势,研究了PCNN对三类图像的分割,并利用最大熵原则选取最佳分割图像。相对于PC平台上MATLAB仿真实现实时性较弱的缺点,研究了基于FPGA平台PCNN二值图像分割的硬件实现,其具有速度快、实时性好等优点,并能取得和MATLAB软件仿真几乎相同的分割结果。相比于传统的PCNN硬件实现,FPGA的实现速度得到显著提高,有着CMOS无法比拟的优势,具有较高应用价值。
Pulse Coupled Neural Network (PCNN) is a new kind of neural network. It was proposed according to the phenomenon of synchronization of impulses which was derived from the observation on the visual cortical neurons of cats, and its feature that similar neurons fire (generate pulses) synchronously is closer to the biological visual characteristic, so the applications of PCNN have caused extensive attention. As a kind of nonlinear dynamic system, PCNN has the chaotic characteristic, but there are few literatures about it. Most of current literatures pay close attention to the research into the simulation of PCNN model, and the PCNN algorithm implementation based on hardware platforms is still a developing hotspot and is becoming a focus of research.
This dissertation focuses on the research into the chaotic characteristic of PCNN and the implementation under FPGA of the maximum entropy segmentation algorithm based on PCNN. The content can be divided into two parts concretely:
1. By means of analyzing the parameter selection of a single neuron in PCNN and the nonlinear characteristic of PCNN, the PCNN model which can generate chaotic characteristic is chased down and analyzed. The stability control to the desired point of the chaotic model and tracking the reference point are studied. Experimental results show that PCNN can generate chaos, can reach the stable control according to desired control points, and can track the reference signal accurately.
2. Taking the advantages of PCNN in image segmentation into account, the segmentation of three types of images based on PCNN is studied and the optimally segmented image is selected on the basis of the principle of maximum entropy. Compared to the algorithm simulation under MATLAB, the implementation of binary image segmentation based on PCNN is characteristic of high speed and strong real-time under the hardware platform of FPGA, while almost the same segmented images can be obtained. Moreover, compared to the traditional hardware implementation of PCNN, the speed under FPGA is increased significantly, so FPGA has the incomparable advantages over CMOS and is of better applied value.
本论文主要进行PCNN混沌特性研究和PCNN最大熵分割算法的FPGA硬件实现研究。具体如下：
1.通过对PCNN单个神经元模型的参数选取及非线性特性分析,分析了PCNN产生混沌特性的模型。对混沌模型如何稳定控制到期望点及对参考信号的跟踪方法进行了研究,实验结果表明,PCNN能产生混沌现象,且能按照期望点进行稳定控制,并能对参考信号进行很好地跟踪。
2.结合PCNN在图像分割方面的优势,研究了PCNN对三类图像的分割,并利用最大熵原则选取最佳分割图像。相对于PC平台上MATLAB仿真实现实时性较弱的缺点,研究了基于FPGA平台PCNN二值图像分割的硬件实现,其具有速度快、实时性好等优点,并能取得和MATLAB软件仿真几乎相同的分割结果。相比于传统的PCNN硬件实现,FPGA的实现速度得到显著提高,有着CMOS无法比拟的优势,具有较高应用价值。
Pulse Coupled Neural Network (PCNN) is a new kind of neural network. It was proposed according to the phenomenon of synchronization of impulses which was derived from the observation on the visual cortical neurons of cats, and its feature that similar neurons fire (generate pulses) synchronously is closer to the biological visual characteristic, so the applications of PCNN have caused extensive attention. As a kind of nonlinear dynamic system, PCNN has the chaotic characteristic, but there are few literatures about it. Most of current literatures pay close attention to the research into the simulation of PCNN model, and the PCNN algorithm implementation based on hardware platforms is still a developing hotspot and is becoming a focus of research.
This dissertation focuses on the research into the chaotic characteristic of PCNN and the implementation under FPGA of the maximum entropy segmentation algorithm based on PCNN. The content can be divided into two parts concretely:
1. By means of analyzing the parameter selection of a single neuron in PCNN and the nonlinear characteristic of PCNN, the PCNN model which can generate chaotic characteristic is chased down and analyzed. The stability control to the desired point of the chaotic model and tracking the reference point are studied. Experimental results show that PCNN can generate chaos, can reach the stable control according to desired control points, and can track the reference signal accurately.
2. Taking the advantages of PCNN in image segmentation into account, the segmentation of three types of images based on PCNN is studied and the optimally segmented image is selected on the basis of the principle of maximum entropy. Compared to the algorithm simulation under MATLAB, the implementation of binary image segmentation based on PCNN is characteristic of high speed and strong real-time under the hardware platform of FPGA, while almost the same segmented images can be obtained. Moreover, compared to the traditional hardware implementation of PCNN, the speed under FPGA is increased significantly, so FPGA has the incomparable advantages over CMOS and is of better applied value.
引文
[1]Hodgkin A L, Huxley A F. A quantitative description of membrane current and its application to conduction and excitation in nerve [J]. J. Physiol,1952,117:500-44.
[2]苏茂君.基于DSP平台的PCNN图像处理技术应用研究[D].兰州大学,2008：3-4.
[3]Eckhorn R, Reitboeck H J, Arndt M, Dicke P. A neural network for future linking via synchronous activity:Results from cat visual cortex and from simulations [C]. In:R, Cotterill (Ed), Models of Brain Function[C], UK:Cambridge University Press,1989:255-272.
[4]Gray C M, singer W. Stimulus-specific neuronal oscillations in the orientation columns of cat visual cortex [J]. Proceedings of the National Academy USA,1989,86(5):1699-1702.
[5]Eckhorn R, Reitboeck H J, Arndt M, Dicke P. Feature linking via synchronization among distributed assemblies:Simulation of results from cat cortex [C]. Neural Computation, MIT Press, 1990,2(3):293-308.
[6]Johnson J L. Pulse-coupled neural nets:Translation, rotation, scale, distortion and intensity signal invariance for images [J]. Appl Opt,1994,33(26):6239～6253.
[7]Ranganath H S, Kuntimad G. Iterative segmentation using pulse coupled neural networks [J]. Proc. SPIE,1996, (2760):543-554.
[8]Plesser H E, Gerstner W. Noise in integrate-and-fire neurons:from stochastic input to escape rates [J]. Neural Computation,2000,12:367-384.
[9]Kistler W M, Van Hemmen J L. Modeling Synaptic Plasticity in Conjunction with the Timing of Pre-and Postsynaptic Action Potentials [J]. Neural computation,2000,12:385-405.
[10]Gustavo Deco, Bernd Schurmann. Spatio-Temporal Coding in the Cortex:Information Flow Based Learning in Spiking Neural Networks [J]. Neural computation,1999,11(4):919-934.
[11]Bressloff, Coombes. Dynamics of strongly-coupled spiking neurons [J]. IEEE Trans, On Neural Networks,2000,12(1)91-129.
[12]Izhikevich E M. Class 1 Neural Excitability, Conventional Synapses Weakly Connected Networks, and Mathematical Foundations of Pulse Coupled Models [J]. IEEE Trans, Neural Networks,1999, 10(3):499-507.
[13]Izhikevich E M. Weakly Pulse-Coupled Oscillators. FM Interactions, Synchronization, and Oscillatory Associative Memory [J]. IEEE Trans, Neural Networks,1999,10(3):508-526.
[14]Haken H. Delay, Noise and phase locking in pulse coupled neural networks [J]. Biosystems,2001, 63(1):15-20.
[15]Ahissar E. Temporal-code to rate-code conversion by neuronal phase-locked loops [J]. Neural Computation,1998,10(3):597-650.
[16]Burkitt A N. An information-theoretic analysis of the coding of a periodic synaptic input by integrate-and-fire neurons [J]. Neurocomputing,2002,44-46,69-74.
[17]马义德,李廉,绽馄,王兆斌.脉冲耦合神经网络与数字图像处理[M].北京：科学出版社,2008.7.
[18]Lindblad T, Kinser J M. Image processing using pulse-coupled neural networks [M].2nd edition. New York:Springer,2005:11-81.
[19]Ranganath H S, Kuntimad G, Johnson J L. Pulse coupled neural networks for image processing [C]. Proceedings of IEEE Southeast Raleigh, NC,1995,3(26～29):37-43.
[20]Kuntimad G, Ranganath H S. Perfect image segmentation using pulse coupled neural networks [J]. IEEE Transactions on Neural Networks,1999,10(3):591-598.
[21]Kinser J M. Recent research in pulse coupled neural networks [C]. SPIE Areosense conf. Orlan, FL, 1996.
[22]赵嘉莉,罗四维,温津伟.基于神经网络的混沌加密算法[J].计算机研究与发展,2001,38(12)：1475-1479.
[23]刘期烈.基于神经网络的混沌控制系统[D].西南交通大学,2004,42：43.
[24]Lapades A, Farbar R. How neural nets works [C]. In:Neural information processing systems; Proceedings of the First IEEE Conference, UNITED STATES Nov,1987:442-456.
[25]Haykin S, Principe J. Making sense of a complex world [J]. IEEE Signal Processing Magazine, 1998,15(3):66-68.
[26]Casdagli M. Nonlinear prediction of chaotic time series [J]. Physica D,1989,35(3):335-356.
[27]Hopfiled J J. Neural networks and physical systems with emergent collective computational abilities [J]. Proc. Natl. Acad. Sci,1982,79(8):2554-2558.
[28]张兴会,刘玲,陈增强.应用Elman神经网络的混沌时间序列预测[J].华东理工大学学报,2002,28(增刊)：30-33.
[29]Ham M, Shi Z W, Wang W. Modeling dynamic system by recurrent neural network with state variables[C]. Proc. Of international Symposium on Neural Networks, Springer,2004,200-205.
[30]Jaeger H. Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the 'echo state network'approach [R]. GMD Report 159, German National Research Center for Information Technology,2002:48.
[31]Rumelhart D E, Hinton G E, Willianms R J. Learning representation by back-propagating errors [J]. Nture,1986,323(9):532-537.
[32]McCulloch W C, Pitts W. A logical calculus of the ideas immanent in nervous activity [J]. Bulletin of Mathematical Biophysics,1943,5:113-114.
[33]Chua L O, Yang L. Cellular neural network:Theory [J]. IEEE Trans, On CAS,1988, 35(10):1256-1273.
[34]Albano A M, Passamante A, Hediger T, Farrell M E. Using neural nets to look for chaos [J]. Physica D,1992,58:1-9.
[35]Gencay R, Liu T. Nonlinear modelling and prediction with feedforward and recurrent networks [J]. Physica D,1997,108(1-2):119-134.
[36]胡玉霞.基于模糊神经网络的混沌时间序列预测[D].郑州大学,2005：3-50.
[37]江亚东,丁丽萍,夏克俭,李格,陈因顽.基于小波神经网络的混沌模式提取[J].北京科技大学学报,23(5)：474-477.
[38]荆涛,徐勇,杨怀江,宋建中.一种基于神经网络的混沌序列产生方法[J].通信学报,1999,20(6)：77-81.
[39]关新平,范正平,彭海朋,王益群.扰动情况下基于RBF网络的混沌系统同步[J].物理学报,2001,50(9)：1670-1674.
[40]谭文,王耀南,刘祖润,周少武.混沌系统的RBF神经网络非线性补偿控制[J].控制理论与应用,2003,20(6)：951-954.
[41]刘丁,任海鹏,孔志强.基于径向基函数神经网络的未知模型混沌系统控制[J].物理学报,2003,52(3)：531-535.
[42]康波,吕炳朝,陈光((?)禹).一种基于神经网络的混沌控制方法[J].系统工程与电子技术,2001,23(5)：11-14.
[43]张家树,肖先赐.基于神经网络的混沌信号源的设计及同步[J].电子与信息学报,2002, 24(1)：37-43.
[44]关新平,唐英干,范正平,王益群.基于神经网络的混沌系统鲁棒自适应同步[J].物理学报,2001,50(11)：2112-2115.
[45]许海霞,王春华,周维,王仕果.基于RBF神经网络的混沌保密通信的研究[J].电路与系统学报,2005,10(3)：28-31.
[46]李征,柯熙政,李芳,尹军.混沌的控制与同步[J].中国科技信息,2005,11(1)：62-63.
[47]王琳,彭建华,陈立宏.改进的OGY法控制超混沌的电路实验研究[J].东北师大学报,2006,38(1)：44-49.
[48]Jackson E A. On the Control of Complex Dynamic Systems [J]. Physica D,1991,50(3):341-366.
[49]Jackson E A. Periodic Entrainment of Chaotic Logistic Map Dynamics [J]. Physica D,1990,44 (3): 407-420.
[50]Vincent T L, Yu J. Control of a Chaotic System [J]. Dynam and Contr Syst,1991,1(5):35-52.
[51]Yamaguchi Y, Ishimura K, Wada M. Chaotic Pulse-Coupled Neural Network as a Model of Synchronization and Desynchronization in Cortex [C]. Proceedings of the 9th International conference on Neural Information Processing (ICONIP'02), Singapore:Orchid Country Club, 2002, Vol(2):571-575.
[52]Waldemark J, Becanovic V, Lindblad T, Lindsey C S. Hybrid Neural Networks for Automatic Target Recognition [C]. IEEE International Conference on Systems, Man, and Cybernetics,1997, 4:4016-4021.
[53]Larsson M, Holmstrom Ch. A study of Pulse Coupled Neural Networks for Feature extraction in Classifying Aurora Borealis [D]. Diploma work, Dept. of Comp. Sci. Umea University, Sweden, 1997.
[54]Chua LO, Yang L. Cellular Neural Networks:Theory [J]. IEEE Trans, Circuits and Systems,1988, 35(10):1257-1272.
[55]Kinget P, Steyaert M S J. A programmable analog cellular neural network CMOS chip for high speed image processing [J]. IEEE Journal of Solid-State Circuits,1995,30(3):235-243.
[56]Ota Y, Wilamowski B M. Analog Implementation of Pulse-coupled Neural Networks [J]. IEEE Trans, On Neural Networks,1999,10(3):539-543.
[57]Frank C, Hartmann G, Ahnk A J, Schafer E M. An Accelerator for Neural Networks:with Pulse-coupled Model Neurons [J]. IEEE Trans, On Neural Networks,1999,10(3):527-538.
[58]John J L, Ritter D. Observation of Periodic Waves in a Pulse-coupled Neural Networks [J]. Opt. Lett,1993,18(15):1253-1255.
[59]Johnson J L. Pulse-coupled Neural Networks, Adaptive Computer; Math, Electron [J]. Opt, SPIE. Crit. Rev,1994(CR55):47-76.
[60]Becanovic V. Diploma Work [R]. KTH, Stockholm, TRITA Report,1996,96:9041.
[61]刘正君.基于脉冲耦合神经网络的图像分割研究[D].哈尔滨工程大学,2008：1-4.
[62]Wilamowski B M, Jaeger R C, Padgett M L, Myers L J. CMOS implementation of a pulse-coupled neuron cell [C]. IEEE International Conference on Neural Networks,1996,2:986～990.
[63]Ota Y, Wilamowski B M. Analog Implementation of Pulse-Coupled Neural Networks [J]. IEEE Trans, On Neural Networks,1999,10(3):539-544.
[64]Chacon M M I, Zimmerman S A, Sanchez A D. A pulse-coupled neural network processor [C]. The 2002 International Joint Conference on Neural Networks,2002,2:1581～1584.
[65]Kinser J M, Lindblad Th. Implementation of the Pulse-Coupled Neural Network in a CNAPS environment [J]. IEEE Trans, On Neural Networks,1999,10(3):591-599.
[66]Lindblad T, Kinser J M. Image Processing Using Pulse Coupled Neural Networks [M]. London: Springer-Verlag,1998:146-151.
[67]Ota, Y. VLSI structure for static image processing with pulse-coupled neural network [C]. IEEE 28th Annual Conference of Industrial Electronics Society,2002,4:3221～3226.
[68]Matolin D, Schreiter J, Schiiffny R. Simulation and implementation of an analog VLSI pulse-coupled neural network for image segmentation [C]. The 47th IEEE International Midwest Symposium on Circuits and Systems,2004,2:397-400.
[69]Gust C. Work presented at the PCNN International Workshop [R]. University of California at San Diego. MICOM, Huntsville,1965, AL 4.
[70]Swain M J, Ballard D. Color indexing [C]. International journal of computer vision,1991, 7(1):11-32
[71]Forchheimer R, Ingelhag P, Jansson C. MAPP2200:A second generation smart optical sensor [J]. in Proc. SPIE, Image Processing and Interchange,1992,1659:2-11.
[72]Waldemark J, Lindblad T, Millberg M. Implementation of a pulse coupled neural network in FPGA [J]. International Journal of Neural Systems,2000,10(3):171—177.
[73]Millberg M, Oberg J, Waldemark J. Generic VHDL Implementation of a PCNN with Loadable Coefficients [J]. Proc.SPIE,1998,3728:186-197.
[74]Vega-Pineda J, Chacon-M I, Camarillo-Cisneros R. Synthesis of pulse-coupled neural networks in FPGAS for real-time image segmentation [C]. IEEE International Joint Conference on Neural Networks,2006,4051-4055.
[75]吴继华,王诚.Altera FPGA/CPLD设计[M].人民邮电出版社,2005,1:3.
[76]Chen G, Lai D. Making a Dynamical systems Chaotic:Feedback Control of Lyapunov Exponents for Discrete-time Dynamical Systems [J]. IEEE Transactions on Circuits and Systems Ⅰ,1997,44 (3):250-253.
[77]Wola A, Swift J B, Swinney H L, Vastano J A. Determining Lyapunov Exponents from a Time Series [J]. Physical D,1985,16 (3):285-317.
[78]姚明海,齐冬莲,赵光宙.基于李雅普诺夫指数的离散混沌系统的控制研究[J].控制与决策,2002,17(2)：171-174.
[79]段广仁.线性系统理论[M].哈尔滨：哈尔滨工业大学出版社,1996,11.
[80]李丽香,彭海朋,卢辉斌,关新平.Henon混沌系统的追踪控制与同步[J].物理学报,2001,50(4)：629-632.
[81]刘福才,王娟,彭海朋,李丽香.Henon混沌系统的预测控制与同步[J].物理学报,2002,51(9)：1954-1959.
[82]Pun T. A New Method for Gray2Level Picture Thresholding Using the Entropy of the Histogram [J]. Signal Processing,1980,2 (2):223-237.
[83]Pun T. Entropic Thresholding [J]. A New Approach. vision, Graph ics, and Image processing, 1981,16(2):210-239.
[84]Pal N R, Pal S K. Entropic thresholding [J]. Signal Processing,1989,16(2):97-108.
[85]Wong A K C, Sahoo P K. A gray2level threshold selection method based on maximum entropy principle [J]. IEEE Transactions on Systems, Man and Cybernetics,1989,19(4):866-871.
[86]Abutaleb A S. Automatic thresholding of gray2level pictures using two-dimensional entropy [J]. Computer Vision, Graphics, and Image Processing,1989,47(1):22-32.
[87]Brink A D. Thresholding of digital images using two-Dimensional entropies [J]. Pattern Recognition,1992,25(8):803-808.
[88]Kapur J N, Sahoo P K, Wong A K C. A new method for gray-level picture thresholding using the entropy of the histogram [J]. Computer Vision, Graphics and Image Processing,1985,29:273-285.
[89]Cheng H D, Chen Y H, Jiang X H. Thresholding using two-dimensional histogram and fuzzy entropy principle [J]. IEEE Trans, Image Processing,2000,9:732-735.
[90]Ma Y D, Dai R L, Li L. A new algorithm of image segmentation based on pulse-coupled neural networks and the entropy of images [C]. The 8th International Conference on Neural Information Processing,2001:273-278.
[91]朱冰,祝小平,余瑞星.基于最大熵和PCNN的图像分割新方法[J].红外技术,2008,30(5)：259-262.
[92]谈国军,戎皓.基于二维最大熵阈值图像分割技术的改进方法[J].软件导刊,2008,7(1)：3-4.
[93]Altera Co. Altera FPGA简介[EB/OL]. http://www.altera.com.
[94]Altera Co. Altera Dec2-70 Handbook [EB/OL]. http://www.altera.com.
[95]Altera Co. Altera Dec2-70 Datasheets [EB/OL]. http://www.altera.com.
[96]潘松,黄继业,曾毓.SOPC技术实用教程[M].北京：清华大学出版社,2005,3.
[97]任爱锋,初秀琴,常存,孙肖子.基于FPGA的嵌入式系统设计[M].西安：西安电子科技大学出版社,2004,1.
[98]赵磊.基于FPGA的图像增强技术的实现[D].昆明理工大学,2008：27-28.
[99]汪国强.SOPC技术及应用[M].北京：机械工业出版社,2006：1-10.
[100]Altera Co, Altera Corporation Quartus Ⅱ简介[EB/OL]. http://www.altera.com.
[101]张永军.基于FPGA的图像处理系统设计与算法实现研究[D].重庆大学,2006：15-24.
[102]Altera Co. QuartusII Handbook [EB/OL]. http://www.altera.com.
[2]苏茂君.基于DSP平台的PCNN图像处理技术应用研究[D].兰州大学,2008：3-4.
[3]Eckhorn R, Reitboeck H J, Arndt M, Dicke P. A neural network for future linking via synchronous activity:Results from cat visual cortex and from simulations [C]. In:R, Cotterill (Ed), Models of Brain Function[C], UK:Cambridge University Press,1989:255-272.
[4]Gray C M, singer W. Stimulus-specific neuronal oscillations in the orientation columns of cat visual cortex [J]. Proceedings of the National Academy USA,1989,86(5):1699-1702.
[5]Eckhorn R, Reitboeck H J, Arndt M, Dicke P. Feature linking via synchronization among distributed assemblies:Simulation of results from cat cortex [C]. Neural Computation, MIT Press, 1990,2(3):293-308.
[6]Johnson J L. Pulse-coupled neural nets:Translation, rotation, scale, distortion and intensity signal invariance for images [J]. Appl Opt,1994,33(26):6239～6253.
[7]Ranganath H S, Kuntimad G. Iterative segmentation using pulse coupled neural networks [J]. Proc. SPIE,1996, (2760):543-554.
[8]Plesser H E, Gerstner W. Noise in integrate-and-fire neurons:from stochastic input to escape rates [J]. Neural Computation,2000,12:367-384.
[9]Kistler W M, Van Hemmen J L. Modeling Synaptic Plasticity in Conjunction with the Timing of Pre-and Postsynaptic Action Potentials [J]. Neural computation,2000,12:385-405.
[10]Gustavo Deco, Bernd Schurmann. Spatio-Temporal Coding in the Cortex:Information Flow Based Learning in Spiking Neural Networks [J]. Neural computation,1999,11(4):919-934.
[11]Bressloff, Coombes. Dynamics of strongly-coupled spiking neurons [J]. IEEE Trans, On Neural Networks,2000,12(1)91-129.
[12]Izhikevich E M. Class 1 Neural Excitability, Conventional Synapses Weakly Connected Networks, and Mathematical Foundations of Pulse Coupled Models [J]. IEEE Trans, Neural Networks,1999, 10(3):499-507.
[13]Izhikevich E M. Weakly Pulse-Coupled Oscillators. FM Interactions, Synchronization, and Oscillatory Associative Memory [J]. IEEE Trans, Neural Networks,1999,10(3):508-526.
[14]Haken H. Delay, Noise and phase locking in pulse coupled neural networks [J]. Biosystems,2001, 63(1):15-20.
[15]Ahissar E. Temporal-code to rate-code conversion by neuronal phase-locked loops [J]. Neural Computation,1998,10(3):597-650.
[16]Burkitt A N. An information-theoretic analysis of the coding of a periodic synaptic input by integrate-and-fire neurons [J]. Neurocomputing,2002,44-46,69-74.
[17]马义德,李廉,绽馄,王兆斌.脉冲耦合神经网络与数字图像处理[M].北京：科学出版社,2008.7.
[18]Lindblad T, Kinser J M. Image processing using pulse-coupled neural networks [M].2nd edition. New York:Springer,2005:11-81.
[19]Ranganath H S, Kuntimad G, Johnson J L. Pulse coupled neural networks for image processing [C]. Proceedings of IEEE Southeast Raleigh, NC,1995,3(26～29):37-43.
[20]Kuntimad G, Ranganath H S. Perfect image segmentation using pulse coupled neural networks [J]. IEEE Transactions on Neural Networks,1999,10(3):591-598.
[21]Kinser J M. Recent research in pulse coupled neural networks [C]. SPIE Areosense conf. Orlan, FL, 1996.
[22]赵嘉莉,罗四维,温津伟.基于神经网络的混沌加密算法[J].计算机研究与发展,2001,38(12)：1475-1479.
[23]刘期烈.基于神经网络的混沌控制系统[D].西南交通大学,2004,42：43.
[24]Lapades A, Farbar R. How neural nets works [C]. In:Neural information processing systems; Proceedings of the First IEEE Conference, UNITED STATES Nov,1987:442-456.
[25]Haykin S, Principe J. Making sense of a complex world [J]. IEEE Signal Processing Magazine, 1998,15(3):66-68.
[26]Casdagli M. Nonlinear prediction of chaotic time series [J]. Physica D,1989,35(3):335-356.
[27]Hopfiled J J. Neural networks and physical systems with emergent collective computational abilities [J]. Proc. Natl. Acad. Sci,1982,79(8):2554-2558.
[28]张兴会,刘玲,陈增强.应用Elman神经网络的混沌时间序列预测[J].华东理工大学学报,2002,28(增刊)：30-33.
[29]Ham M, Shi Z W, Wang W. Modeling dynamic system by recurrent neural network with state variables[C]. Proc. Of international Symposium on Neural Networks, Springer,2004,200-205.
[30]Jaeger H. Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the 'echo state network'approach [R]. GMD Report 159, German National Research Center for Information Technology,2002:48.
[31]Rumelhart D E, Hinton G E, Willianms R J. Learning representation by back-propagating errors [J]. Nture,1986,323(9):532-537.
[32]McCulloch W C, Pitts W. A logical calculus of the ideas immanent in nervous activity [J]. Bulletin of Mathematical Biophysics,1943,5:113-114.
[33]Chua L O, Yang L. Cellular neural network:Theory [J]. IEEE Trans, On CAS,1988, 35(10):1256-1273.
[34]Albano A M, Passamante A, Hediger T, Farrell M E. Using neural nets to look for chaos [J]. Physica D,1992,58:1-9.
[35]Gencay R, Liu T. Nonlinear modelling and prediction with feedforward and recurrent networks [J]. Physica D,1997,108(1-2):119-134.
[36]胡玉霞.基于模糊神经网络的混沌时间序列预测[D].郑州大学,2005：3-50.
[37]江亚东,丁丽萍,夏克俭,李格,陈因顽.基于小波神经网络的混沌模式提取[J].北京科技大学学报,23(5)：474-477.
[38]荆涛,徐勇,杨怀江,宋建中.一种基于神经网络的混沌序列产生方法[J].通信学报,1999,20(6)：77-81.
[39]关新平,范正平,彭海朋,王益群.扰动情况下基于RBF网络的混沌系统同步[J].物理学报,2001,50(9)：1670-1674.
[40]谭文,王耀南,刘祖润,周少武.混沌系统的RBF神经网络非线性补偿控制[J].控制理论与应用,2003,20(6)：951-954.
[41]刘丁,任海鹏,孔志强.基于径向基函数神经网络的未知模型混沌系统控制[J].物理学报,2003,52(3)：531-535.
[42]康波,吕炳朝,陈光((?)禹).一种基于神经网络的混沌控制方法[J].系统工程与电子技术,2001,23(5)：11-14.
[43]张家树,肖先赐.基于神经网络的混沌信号源的设计及同步[J].电子与信息学报,2002, 24(1)：37-43.
[44]关新平,唐英干,范正平,王益群.基于神经网络的混沌系统鲁棒自适应同步[J].物理学报,2001,50(11)：2112-2115.
[45]许海霞,王春华,周维,王仕果.基于RBF神经网络的混沌保密通信的研究[J].电路与系统学报,2005,10(3)：28-31.
[46]李征,柯熙政,李芳,尹军.混沌的控制与同步[J].中国科技信息,2005,11(1)：62-63.
[47]王琳,彭建华,陈立宏.改进的OGY法控制超混沌的电路实验研究[J].东北师大学报,2006,38(1)：44-49.
[48]Jackson E A. On the Control of Complex Dynamic Systems [J]. Physica D,1991,50(3):341-366.
[49]Jackson E A. Periodic Entrainment of Chaotic Logistic Map Dynamics [J]. Physica D,1990,44 (3): 407-420.
[50]Vincent T L, Yu J. Control of a Chaotic System [J]. Dynam and Contr Syst,1991,1(5):35-52.
[51]Yamaguchi Y, Ishimura K, Wada M. Chaotic Pulse-Coupled Neural Network as a Model of Synchronization and Desynchronization in Cortex [C]. Proceedings of the 9th International conference on Neural Information Processing (ICONIP'02), Singapore:Orchid Country Club, 2002, Vol(2):571-575.
[52]Waldemark J, Becanovic V, Lindblad T, Lindsey C S. Hybrid Neural Networks for Automatic Target Recognition [C]. IEEE International Conference on Systems, Man, and Cybernetics,1997, 4:4016-4021.
[53]Larsson M, Holmstrom Ch. A study of Pulse Coupled Neural Networks for Feature extraction in Classifying Aurora Borealis [D]. Diploma work, Dept. of Comp. Sci. Umea University, Sweden, 1997.
[54]Chua LO, Yang L. Cellular Neural Networks:Theory [J]. IEEE Trans, Circuits and Systems,1988, 35(10):1257-1272.
[55]Kinget P, Steyaert M S J. A programmable analog cellular neural network CMOS chip for high speed image processing [J]. IEEE Journal of Solid-State Circuits,1995,30(3):235-243.
[56]Ota Y, Wilamowski B M. Analog Implementation of Pulse-coupled Neural Networks [J]. IEEE Trans, On Neural Networks,1999,10(3):539-543.
[57]Frank C, Hartmann G, Ahnk A J, Schafer E M. An Accelerator for Neural Networks:with Pulse-coupled Model Neurons [J]. IEEE Trans, On Neural Networks,1999,10(3):527-538.
[58]John J L, Ritter D. Observation of Periodic Waves in a Pulse-coupled Neural Networks [J]. Opt. Lett,1993,18(15):1253-1255.
[59]Johnson J L. Pulse-coupled Neural Networks, Adaptive Computer; Math, Electron [J]. Opt, SPIE. Crit. Rev,1994(CR55):47-76.
[60]Becanovic V. Diploma Work [R]. KTH, Stockholm, TRITA Report,1996,96:9041.
[61]刘正君.基于脉冲耦合神经网络的图像分割研究[D].哈尔滨工程大学,2008：1-4.
[62]Wilamowski B M, Jaeger R C, Padgett M L, Myers L J. CMOS implementation of a pulse-coupled neuron cell [C]. IEEE International Conference on Neural Networks,1996,2:986～990.
[63]Ota Y, Wilamowski B M. Analog Implementation of Pulse-Coupled Neural Networks [J]. IEEE Trans, On Neural Networks,1999,10(3):539-544.
[64]Chacon M M I, Zimmerman S A, Sanchez A D. A pulse-coupled neural network processor [C]. The 2002 International Joint Conference on Neural Networks,2002,2:1581～1584.
[65]Kinser J M, Lindblad Th. Implementation of the Pulse-Coupled Neural Network in a CNAPS environment [J]. IEEE Trans, On Neural Networks,1999,10(3):591-599.
[66]Lindblad T, Kinser J M. Image Processing Using Pulse Coupled Neural Networks [M]. London: Springer-Verlag,1998:146-151.
[67]Ota, Y. VLSI structure for static image processing with pulse-coupled neural network [C]. IEEE 28th Annual Conference of Industrial Electronics Society,2002,4:3221～3226.
[68]Matolin D, Schreiter J, Schiiffny R. Simulation and implementation of an analog VLSI pulse-coupled neural network for image segmentation [C]. The 47th IEEE International Midwest Symposium on Circuits and Systems,2004,2:397-400.
[69]Gust C. Work presented at the PCNN International Workshop [R]. University of California at San Diego. MICOM, Huntsville,1965, AL 4.
[70]Swain M J, Ballard D. Color indexing [C]. International journal of computer vision,1991, 7(1):11-32
[71]Forchheimer R, Ingelhag P, Jansson C. MAPP2200:A second generation smart optical sensor [J]. in Proc. SPIE, Image Processing and Interchange,1992,1659:2-11.
[72]Waldemark J, Lindblad T, Millberg M. Implementation of a pulse coupled neural network in FPGA [J]. International Journal of Neural Systems,2000,10(3):171—177.
[73]Millberg M, Oberg J, Waldemark J. Generic VHDL Implementation of a PCNN with Loadable Coefficients [J]. Proc.SPIE,1998,3728:186-197.
[74]Vega-Pineda J, Chacon-M I, Camarillo-Cisneros R. Synthesis of pulse-coupled neural networks in FPGAS for real-time image segmentation [C]. IEEE International Joint Conference on Neural Networks,2006,4051-4055.
[75]吴继华,王诚.Altera FPGA/CPLD设计[M].人民邮电出版社,2005,1:3.
[76]Chen G, Lai D. Making a Dynamical systems Chaotic:Feedback Control of Lyapunov Exponents for Discrete-time Dynamical Systems [J]. IEEE Transactions on Circuits and Systems Ⅰ,1997,44 (3):250-253.
[77]Wola A, Swift J B, Swinney H L, Vastano J A. Determining Lyapunov Exponents from a Time Series [J]. Physical D,1985,16 (3):285-317.
[78]姚明海,齐冬莲,赵光宙.基于李雅普诺夫指数的离散混沌系统的控制研究[J].控制与决策,2002,17(2)：171-174.
[79]段广仁.线性系统理论[M].哈尔滨：哈尔滨工业大学出版社,1996,11.
[80]李丽香,彭海朋,卢辉斌,关新平.Henon混沌系统的追踪控制与同步[J].物理学报,2001,50(4)：629-632.
[81]刘福才,王娟,彭海朋,李丽香.Henon混沌系统的预测控制与同步[J].物理学报,2002,51(9)：1954-1959.
[82]Pun T. A New Method for Gray2Level Picture Thresholding Using the Entropy of the Histogram [J]. Signal Processing,1980,2 (2):223-237.
[83]Pun T. Entropic Thresholding [J]. A New Approach. vision, Graph ics, and Image processing, 1981,16(2):210-239.
[84]Pal N R, Pal S K. Entropic thresholding [J]. Signal Processing,1989,16(2):97-108.
[85]Wong A K C, Sahoo P K. A gray2level threshold selection method based on maximum entropy principle [J]. IEEE Transactions on Systems, Man and Cybernetics,1989,19(4):866-871.
[86]Abutaleb A S. Automatic thresholding of gray2level pictures using two-dimensional entropy [J]. Computer Vision, Graphics, and Image Processing,1989,47(1):22-32.
[87]Brink A D. Thresholding of digital images using two-Dimensional entropies [J]. Pattern Recognition,1992,25(8):803-808.
[88]Kapur J N, Sahoo P K, Wong A K C. A new method for gray-level picture thresholding using the entropy of the histogram [J]. Computer Vision, Graphics and Image Processing,1985,29:273-285.
[89]Cheng H D, Chen Y H, Jiang X H. Thresholding using two-dimensional histogram and fuzzy entropy principle [J]. IEEE Trans, Image Processing,2000,9:732-735.
[90]Ma Y D, Dai R L, Li L. A new algorithm of image segmentation based on pulse-coupled neural networks and the entropy of images [C]. The 8th International Conference on Neural Information Processing,2001:273-278.
[91]朱冰,祝小平,余瑞星.基于最大熵和PCNN的图像分割新方法[J].红外技术,2008,30(5)：259-262.
[92]谈国军,戎皓.基于二维最大熵阈值图像分割技术的改进方法[J].软件导刊,2008,7(1)：3-4.
[93]Altera Co. Altera FPGA简介[EB/OL]. http://www.altera.com.
[94]Altera Co. Altera Dec2-70 Handbook [EB/OL]. http://www.altera.com.
[95]Altera Co. Altera Dec2-70 Datasheets [EB/OL]. http://www.altera.com.
[96]潘松,黄继业,曾毓.SOPC技术实用教程[M].北京：清华大学出版社,2005,3.
[97]任爱锋,初秀琴,常存,孙肖子.基于FPGA的嵌入式系统设计[M].西安：西安电子科技大学出版社,2004,1.
[98]赵磊.基于FPGA的图像增强技术的实现[D].昆明理工大学,2008：27-28.
[99]汪国强.SOPC技术及应用[M].北京：机械工业出版社,2006：1-10.
[100]Altera Co, Altera Corporation Quartus Ⅱ简介[EB/OL]. http://www.altera.com.
[101]张永军.基于FPGA的图像处理系统设计与算法实现研究[D].重庆大学,2006：15-24.
[102]Altera Co. QuartusII Handbook [EB/OL]. http://www.altera.com.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |