复杂环境下基于神经网络的工件识别与机器人智能抓取
|
摘要
智能机器人之所以区别于传统的示教-再现型机器人,是因为其有感知外部世界变化并作出自适应调整的能力。在众多的机器人感觉中,尤以视觉应用最广。而在复杂工业现场环境下,存在诸如粉尘、光照变化、摄像机抖动、遮挡、信道传输噪声等干扰因素,不可避免地会对机器人的视觉产生影响,造成图像信号的降质。此外,复杂多变的工作环境,也给传统的需要标定技术才能完成的机器人控制器的设计造成困难。针对上述问题,本文以基于视觉的机器人智能分拣和抓取为应用背景,利用神经网络研究复杂环境下图像的恢复和目标识别以及机器人视觉伺服控制。
神经网络固有的非线性逼近能力、自适应和泛化能力,以及联想记忆能力,使其成为贯穿本文各个研究部分的关键技术。其中,复值神经网络以其自然的复数处理能力,使得图像等常需频域处理的信号有了直接的表达和处理方式。
为解决恶劣环境下图像降质严重的问题,本文利用复值Hopfield神经网络的联想记忆能力完成对降质图像的恢复。为此本文首先开展复值Hopfield神经网络的分析和综合研究。在此基础上,讨论复杂环境下图像识别和恢复的实现问题,最后基于模糊行为规则和神经网络对机器人智能视觉伺服控制器进行设计。归结起来,本文的主要研究工作包括:
1)针对一类复值离散时间Hopfield神经网络,提出一种兼顾平衡条件和稳定条件的网络综合方法。该方法首先根据稳定性分析,得出系统局部渐近稳定性判决条件,而后通过求解网络平衡方程和调整平衡解中的激活函数增益,确保最后的网络综合结果满足稳定性判据,从而使每个待记忆模式在网络中是稳定且吸引的。
2)针对一类复值连续时间Hopfield神经网络,提出一种吸引域受限条件下兼顾平衡条件和稳定条件的网络综合方法。该方法首先在复值域中构造基于吸引域参数的Lyapunov函数,而后开展系统的稳定性分析,并分别在网络时间常数已知和未知的情况下,进行吸引域受限条件下的网络综合研究。其中平衡方程的求解分别基于伪逆规则和奇异值分解技术,所得网络参数约束和给定的吸引域参数均包含在用线性矩阵不等式表示的渐近稳定判据中,所以网络参数易于求解,且所得结果能同时满足给定吸引域内记忆模式的稳定性和吸引性。
3)针对一类可直接表示灰度等多值图像的复多值Hopfield神经网络,提出一种兼顾平衡条件和能量函数逐步递减要求的网络综合方法。综合中基于奇异值分解技术求得的网络平衡方程通解,依能量函数递减原则进行调整,并最终得到能同时满足稳定性和吸引性要求的网络权值解,保证了图像联想记忆的可靠性。
4)针对复杂环境下图像易出现模糊、缺损、噪声污染等严重降质的问题,通过引入复多值单层感知机完成对降质图像中各种形态工件的图像识别;利用3)中提出的一种复多值Hopfield联想记忆器完成对工件降质图像的恢复,进而实现对工件上角点信息的可靠提取,为机器人的视觉伺服控制提供可靠的图像反馈信息;
5)针对复杂多变的非结构化环境中,常规的基于图像雅克比矩阵的视觉伺服控制存在建模困难且适应能力差的问题,提出一种基于模糊行为和神经网络的两阶段机器人智能抓取控制方案。其中第一阶段的模糊行为控制模仿了人的控制经验,可完成对机器人手爪的粗略定位;第二阶段的神经网络控制则利用BP神经网络的非线性逼近能力,实现对从图像空间到机器人关节空间的复杂非线性系统建模,完成对机器人手爪的准确位姿控制。
Intelligent robot has the ability to perceive and acclimatize itself to the environment around it. So it is very different from conventional playback robot. Among the various senses of robot, vision is the most popular one. However, when robot works in complicated industrial environment, there are many disturbance factors to degrade the image signals, such as dust, variation of illumination, vibration of camera, shielding, noise in signal channel, etc. Besides these problems, the complicated and variable work environment makes it very difficult to design robot controller by conventional calibration technique. For these reasons, considering the sorting and griping manipulation of robot in the complicated industrial environment, this thesis discusses the problem of image restoration and recognition and visual servoing control for robot based on neural networks.
Neural networks are herein the key technology permeating throughout this thesis for their abilities in nonlinear approximation, adaptation, generalization and associative memory, among which the complex-valued neural networks are capable naturally to process complex number, thus can be used to denote and process frequency signals directly, such as the image expressing in frequency domain.
In order to solve the image degraded problem resulting from bad visual environment, complex-valued Hopfield neural network functioned as associative memory is utilized for image restoration in this thesis. Thus the analysis and synthesis of several kinds of complex-valued Hopfield neural networks are studied firstly. And based on such research results the image recognition and restoration are completed in complicated environment. This thesis also discusses the designation of visual servoing controller for robot by fuzzy behavior rules and neural network control. The main work in this thesis can be summarized as follows:
1) Propose a synthesis method for a class of complex-valued discrete time Hopfield neural network, where the equilibrium condition and stability criterion are both satisfied. In this method, a local asymptotic stable condition is derived firstly and used to decide whether the solution of equilibrium equations is accepted. And if no, a gain-regulation of the neuron activation function is carried and guarantees finally both the stability and attractive ability for every storage patterns.
2) Propose a synthesis method for a class of complex-valued continuous time Hopfield neural network under constrained attractive domain, which can satisfy the stable condition and equilibrium condition. In this method, this thesis constructs a Lyapunov function in complex-valued domain where the parameter of attractive domain is contained, and then analyses stability of the network. Considering two situations about time constants of the system, i.e. unknown or known, the corresponding solving algorithm is Pseudo-inverse and singular values decompose, respectively. The constraints of network parameters derived from equilibrium equations, together with the parameters of attractive domain, are denoted in the asymptotic stable condition which can be rewritten as linear matrix inequations. As a result, the network这“parameters can be solved easily and guarantee the storage patterns are both stable and attractive in the given attractive domain.
3) Propose a synthesis method for a class of complex multi-valued Hopfield neural network used to express and process multi-valued information, for example, gray image where both the equilibrium condition and the requirement for energy function decreasing are considered. In this method a general solution of network equilibrium equation solved by singular value decomposition technique is adjusted according to the rule of decreasing the energy function. The final network weights can satisfy both stability and attraction, thus guarantee the reliable association memory of gray images.
4) Study the image recognition for workpieces with different shape where the images are badly degraded by blur, defect or noise pollution because of the complicated industrial environment. The solution for degraded image recognition is to apply a class of complex-valued single layer perceptron. The proposed energy decreasing synthesis method by 3) for complex-valued Hopfield association and memory is utilized for restoring the degraded image, which can provide more reliable corner point information of the workpiece for the next grasping manipulation of robot.
5) Propose a fuzzy behavior and neural network based visual servoing control scheme for intelligent grasping of the robot by the reason that the conventional visual servoing control method, i.e. image Jacobian matrix based method, has difficulties in modeling and its adaptive capacity is bad when robot works in a complicated and multivariate environment. The first phase of the scheme is fuzzy control which simulates the human control experience and be used to rough position for the clamp holder of the robot. And the second phase is neural network based control which applies the nonlinear approximation capability of BP network to model the nonlinear mapping from the image space to the joint space of the robot, and thus to complete the accurate position and orientation control of the clamp holder of robot.
神经网络固有的非线性逼近能力、自适应和泛化能力,以及联想记忆能力,使其成为贯穿本文各个研究部分的关键技术。其中,复值神经网络以其自然的复数处理能力,使得图像等常需频域处理的信号有了直接的表达和处理方式。
为解决恶劣环境下图像降质严重的问题,本文利用复值Hopfield神经网络的联想记忆能力完成对降质图像的恢复。为此本文首先开展复值Hopfield神经网络的分析和综合研究。在此基础上,讨论复杂环境下图像识别和恢复的实现问题,最后基于模糊行为规则和神经网络对机器人智能视觉伺服控制器进行设计。归结起来,本文的主要研究工作包括:
1)针对一类复值离散时间Hopfield神经网络,提出一种兼顾平衡条件和稳定条件的网络综合方法。该方法首先根据稳定性分析,得出系统局部渐近稳定性判决条件,而后通过求解网络平衡方程和调整平衡解中的激活函数增益,确保最后的网络综合结果满足稳定性判据,从而使每个待记忆模式在网络中是稳定且吸引的。
2)针对一类复值连续时间Hopfield神经网络,提出一种吸引域受限条件下兼顾平衡条件和稳定条件的网络综合方法。该方法首先在复值域中构造基于吸引域参数的Lyapunov函数,而后开展系统的稳定性分析,并分别在网络时间常数已知和未知的情况下,进行吸引域受限条件下的网络综合研究。其中平衡方程的求解分别基于伪逆规则和奇异值分解技术,所得网络参数约束和给定的吸引域参数均包含在用线性矩阵不等式表示的渐近稳定判据中,所以网络参数易于求解,且所得结果能同时满足给定吸引域内记忆模式的稳定性和吸引性。
3)针对一类可直接表示灰度等多值图像的复多值Hopfield神经网络,提出一种兼顾平衡条件和能量函数逐步递减要求的网络综合方法。综合中基于奇异值分解技术求得的网络平衡方程通解,依能量函数递减原则进行调整,并最终得到能同时满足稳定性和吸引性要求的网络权值解,保证了图像联想记忆的可靠性。
4)针对复杂环境下图像易出现模糊、缺损、噪声污染等严重降质的问题,通过引入复多值单层感知机完成对降质图像中各种形态工件的图像识别;利用3)中提出的一种复多值Hopfield联想记忆器完成对工件降质图像的恢复,进而实现对工件上角点信息的可靠提取,为机器人的视觉伺服控制提供可靠的图像反馈信息;
5)针对复杂多变的非结构化环境中,常规的基于图像雅克比矩阵的视觉伺服控制存在建模困难且适应能力差的问题,提出一种基于模糊行为和神经网络的两阶段机器人智能抓取控制方案。其中第一阶段的模糊行为控制模仿了人的控制经验,可完成对机器人手爪的粗略定位;第二阶段的神经网络控制则利用BP神经网络的非线性逼近能力,实现对从图像空间到机器人关节空间的复杂非线性系统建模,完成对机器人手爪的准确位姿控制。
Intelligent robot has the ability to perceive and acclimatize itself to the environment around it. So it is very different from conventional playback robot. Among the various senses of robot, vision is the most popular one. However, when robot works in complicated industrial environment, there are many disturbance factors to degrade the image signals, such as dust, variation of illumination, vibration of camera, shielding, noise in signal channel, etc. Besides these problems, the complicated and variable work environment makes it very difficult to design robot controller by conventional calibration technique. For these reasons, considering the sorting and griping manipulation of robot in the complicated industrial environment, this thesis discusses the problem of image restoration and recognition and visual servoing control for robot based on neural networks.
Neural networks are herein the key technology permeating throughout this thesis for their abilities in nonlinear approximation, adaptation, generalization and associative memory, among which the complex-valued neural networks are capable naturally to process complex number, thus can be used to denote and process frequency signals directly, such as the image expressing in frequency domain.
In order to solve the image degraded problem resulting from bad visual environment, complex-valued Hopfield neural network functioned as associative memory is utilized for image restoration in this thesis. Thus the analysis and synthesis of several kinds of complex-valued Hopfield neural networks are studied firstly. And based on such research results the image recognition and restoration are completed in complicated environment. This thesis also discusses the designation of visual servoing controller for robot by fuzzy behavior rules and neural network control. The main work in this thesis can be summarized as follows:
1) Propose a synthesis method for a class of complex-valued discrete time Hopfield neural network, where the equilibrium condition and stability criterion are both satisfied. In this method, a local asymptotic stable condition is derived firstly and used to decide whether the solution of equilibrium equations is accepted. And if no, a gain-regulation of the neuron activation function is carried and guarantees finally both the stability and attractive ability for every storage patterns.
2) Propose a synthesis method for a class of complex-valued continuous time Hopfield neural network under constrained attractive domain, which can satisfy the stable condition and equilibrium condition. In this method, this thesis constructs a Lyapunov function in complex-valued domain where the parameter of attractive domain is contained, and then analyses stability of the network. Considering two situations about time constants of the system, i.e. unknown or known, the corresponding solving algorithm is Pseudo-inverse and singular values decompose, respectively. The constraints of network parameters derived from equilibrium equations, together with the parameters of attractive domain, are denoted in the asymptotic stable condition which can be rewritten as linear matrix inequations. As a result, the network这“parameters can be solved easily and guarantee the storage patterns are both stable and attractive in the given attractive domain.
3) Propose a synthesis method for a class of complex multi-valued Hopfield neural network used to express and process multi-valued information, for example, gray image where both the equilibrium condition and the requirement for energy function decreasing are considered. In this method a general solution of network equilibrium equation solved by singular value decomposition technique is adjusted according to the rule of decreasing the energy function. The final network weights can satisfy both stability and attraction, thus guarantee the reliable association memory of gray images.
4) Study the image recognition for workpieces with different shape where the images are badly degraded by blur, defect or noise pollution because of the complicated industrial environment. The solution for degraded image recognition is to apply a class of complex-valued single layer perceptron. The proposed energy decreasing synthesis method by 3) for complex-valued Hopfield association and memory is utilized for restoring the degraded image, which can provide more reliable corner point information of the workpiece for the next grasping manipulation of robot.
5) Propose a fuzzy behavior and neural network based visual servoing control scheme for intelligent grasping of the robot by the reason that the conventional visual servoing control method, i.e. image Jacobian matrix based method, has difficulties in modeling and its adaptive capacity is bad when robot works in a complicated and multivariate environment. The first phase of the scheme is fuzzy control which simulates the human control experience and be used to rough position for the clamp holder of the robot. And the second phase is neural network based control which applies the nonlinear approximation capability of BP network to model the nonlinear mapping from the image space to the joint space of the robot, and thus to complete the accurate position and orientation control of the clamp holder of robot.
引文
[1] [美] Saeed B. Niku.著.机器人学导论——分析、系统及应用[M].孙富春等译.北京:电子工业出版社. 2004
[2]赵清杰,连广宇.机器人视觉伺服综述[J].控制与决策, 2001,16(6): 849-853
[3]李新.面向神经计算的视觉信息处理研究[D].西北工业大学博士学位论文. 2002
[4]王丹青,李志俊.基于神经网络的工业图像识别[J].武汉科技大学学报(自然科学版) , 2005, 28(4): 387-390
[5] Costantini G, Casali D, Perfetti R. Neural associative memory storing gray-coded gray-scale images [J]. IEEE Trans. on Neural Networks, 2003, 14(3): 703-707
[6] Aizenberg I, Butakoff C. Neural network based on multi-valued neurons and its applications to image recognition and blur recognition[C]. Proc. SPIE - The International Society for Optical Engineering, 2001, 4305: 11-21,
[7] Hirose A. Complex-valued neural networks: theories and applications [M]. World Scientific Series on Innovation Intelligence, vol 5, Singapore: World Scientific Publishing Co. Pte. Ltd. 2003
[8] Hideki H, Takashi K, Motoo S, et al. Visual control of robotic manipulator based on neural networks. IEEE Trans. on Industrial Electronics, 1992, 39(6): 490-496
[9]林靖,陈辉堂.机器人视觉伺服系统的研究[J].控制理论与应用, 2000, 17(4):476-481
[10]焦李成.神经网络系统理论[M ].西安:西安电子科技大学出版社, 1991
[11]何玉彬,李新忠.神经网络控制及其应用[M ].北京:科学出版社, 2000
[12] McCulloch W S, Pitts W A. A logical calculus of the ideas immanent in nervous activity [J]. Bulletin of Mathematical Biophysics, 1943, 5: 115-133
[13] Hebb D O. The Organization of Behavious [M]. New York, John Wiley & Sons Inc., 1949
[14] Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain [J]. Psychology Review, 1958, 65: 386-408
[15] Minsky M, Papert S. Perceptron [M]. Cambridge, MA: MIT Press, 1969
[16] Hopfield J J. Neural networks and physical systems with emergent collective computational abilities[C]. Proceeding of the National Academy of Science. USA (Biophysics), 1982, 79: 2554-2558
[17] Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons[C]. Proceedins of the National Academy of Science, USA(Biophysics), 1984, 81:3088-3092
[18] Chua L O and Yang L. Cellular neural networks: theory [J]. IEEE Trans. on Circuits and Systems, 1988, 35:1257-1272
[19]徐立中,刘富强.基于模型的工业图像增强技术[J].仪器仪表学报, 1999, 20(6):609-611
[20]黎明,严超华,刘高航.基于前向神经网络和Hopfield反馈神经网络的边界检测法[J].中国图象图形学报. 1999, 4 (8): 663-667
[21] Chao C H, Dhawan A P. Edge detection using a Hopfield neural network [J]. Optical Engineering, 1994(33): 3739-3747
[22] Qiu G, Varley M R, Terrell T J. Improved block truncation coding using Hopfield neural network[J]. Electronics Letters, 1991, 27 (21): 1924-1926
[23]马向玲,田宝国. Hopfield网络应用实例分析[J].计算机仿真, 2003, 20(8): 64-66
[24]张敏瑞,张丽娜,黄兴.基于神经网络自联想的数字图像水印算法[J].江西师范大学学报(自然科学版) , 2007, 31(5): 445-449
[25]王宇,何小祥.改进的网络图像复原[J].计算机工程, 2007, 33(17): 54-57
[26]李云栋,张其善.基于联想记忆的彩色图像自适应预测编码方法[J].信号处理, 2006, 22(2): 137-140
[27]周日贵,姜楠,丁秋林.量子Hopfield神经网络及图像识别[J].中国图象图形学报, 2008,13(1): 119-123
[28]吴锡生,王士同.模糊形态联想记忆网络及其在细胞图像联想识别中的应用[J].中国图象图形学报, 2006, 11(10): 1450-1455
[29]叶旭,李志能,陈抗生.基于矢量量化及Hopfield模型的灰度级图像识别[J].光学学报, 1998, 18: 112-115
[30] Widrow B, McCool J, Ball M. The complex LMS algorithm [C]. Proc. IEEE, 1975, 63(4): 719–720
[31] Georgiou, G M, Koutsougeras, C. Complex domain backpropagation [J]. IEEE Trans. on Circuits and Systems II: Analog and Digital Signal Processing, 1992, 39(5): 330-334
[32] Aizenberg N N, Ivaskiv Y L, Pospelov D A. About one generalization of the threshold function [J]. Doklady Akademii Nauk SSSR (The Reports of the Academy of Sciences of the USSR), 1971, 196(6): 1287-1290 (in Russian)
[33] Aizenberg I, Paliy D, Astola J T. Multilayer neural network based on multi-valued neurons and the blur identification problem [C]. 2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006, 473-479
[34]钟守铭,刘碧森,王晓梅等.神经网络稳定性理论[M].北京:科学出版, 2008
[35]廖晓昕.动力系统的稳定性理论和应用[M].北京:国防工业出版社, 2000
[36] Kuroe Y, Hashimoto N, Mori T. On energy function for complex-valued neural networks and its applications[C]. Proceedings of the 9th International Conference on Neural Information Processing (ICONIP'02) , 2002, 3:1079-1083
[37] Special session on“Complex-valued neural networks and their applications”in Knowledge-Based Intelligent Information Engineering System & Allied Technologies, KES2001, Part 1, 10s Press, Tokyo, 2001, 550-580
[38] Kuroe Y, Yoshida M, Mori T. On Activation functions for complex-Valued neuralnetworks–existence of energy functions[C]. International Conference on Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP 2003), 2003, 985–992
[39] Mishra D, Tolambiya A, Shukla A, et al. Stability analysis for higher order complex-valued Hopfield neural network[C]. Proceedings of the 13th International Conference on Neural Information Processing (ICONIP'06) Part I, LNCS 4232, 2006, 608–615
[40] Kuroe Y, Taniguchi Y. Models of self-correlation type complex-valued associative memories and their dynamics[C]. International Conference on Artificial Neural Networks (ICANN 2005), LNCS 3696, 2005, 185-192
[41] Kuroe Y, Taniguchi Y. Models of self-correlation type complex-valued associative memories and their performance comparison[C]. 2006 International Joint Conference on Neural Networks, Vancouver, BC, Canada July 16-21, 2006, 213-217
[42] Hirose A. Dynamics of fully complex-valued neural networks [J]. Electronics Letters, 1992, 28(16): 1492-1494
[43] Kuroe Y, Hashimoto N, Mori T. Qualitative analysis of a self-correlation type complex valued associative memories [J]. Nonlinear Analysis, 2001, 47(9):5795-5806
[44] Kuroe Y, Hashimoto N, Mori T. Qualitative analysis of continuous complex-valued associative memories[C]. International Conference on Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP 2001), 2001, 843 -850
[45] Lee D L. Relaxation of the stability condition of the complex-valued neural networks[J] . IEEE Trans. on Neural Networks, 2001, 12(5): 1260-1262
[46] Lee D L. Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule [J]. IEEE Trans. on Neural Networks, 2001, 12(2): 439–443
[47] Lee D L. New stability conditions for Hopfield networks in partial simultaneous update model [J]. IEEE Trans. on Neural Networks, 1999, 10(4): 975–978
[48] Xu Z B, Kwong C P. Global convergence and asymptotic stability of asymmetric Hopfield networks [J]. Journal of Mathematical Analysis and Applications, 1995,191(3): 405–427
[49] Xu Z B, Hu G Q, Kwong C P. Asymmetric Hopfield networks: theory and applications [J]. Neural Networks, 1996, 9(3): 483–501
[50] Vidyasagar M. Location and stability of the high-gain equilibria of nonlinear neural networks [J]. IEEE Trans. on Neural Networks, 1993, 4(4): 660–672
[51] Morita M. Memory and learning of sequential patterns by nonmonotone neural networks [J]. Neural Networks, 1996, 9(8): 1477–1489
[52] Hirose A. Continuous complex-valued back-propagation learning [J]. Electronics Letters, 1992, 28(20): 1854–1855
[53] Hirose A. Proposal of fully complex-valued neural networks[C]. International Joint Conference on Neural Networks(IJCNN1992), 1992, 4: 152–157
[54] Hirose A, Onishi H. Proposal of relative-minimization learning for behavior stabilization of complex-valued recurrent neural networks [J]. Neurocomputing, 1999, 24: 163-171
[55] Benvenuto N, Piazza F. On the complex backpropagation algorithm [J]. IEEE Trans. on Signal Processing, 1992,40(4): 967–969
[56] Hanna A I, Mandic D P. A fully adaptive normalized nonlinear gradient descent algorithm for complex-valued nonlinear adaptive filters [J]. IEEE Trans. on signal processing, 2003, 51(10): 2540-2549
[57] Chen X M, Zheng T, Variappan C. A modified error backpropagation algorithm for complex-value neural networks [J]. International Journal of Neural Systems, 2005, 15( 6): 435–443
[58] Personnaz L, Guyon I, Dreyfus G. Collective computational properties of neural networks: New learning mechanisms [J]. Physical Review Online Archive, 1986, A34: 4217–4228
[59] Personnaz L, Guyon I, Dreyfus G, et al. A biologically constrained learning mechanism in networks of formal neurons[J], Journal of Statistical Physics,1986, 43(3-4): 411–422
[60] Jankowski S, Lozowski A, Zurada J M. Complex-valued multistate neural associative memory [J]. IEEE Trans. Neural Networks, 1996, 7(6): 1491–1496
[61] Lee D L. Improvements of complex-valued Hopfield associative memory by using generalized projection rules [J]. IEEE Trans. on Neural Networks, 2006, 17(5): 1341-1347
[62] Muezzinoglu M K, Guzelis C, Zurada J M. A new design method for the complex-valued multistate Hopfield associative memory [J]. IEEE Trans. on Neural Networks, 2003, 14(4): 891–899
[63] Zurada J M, Cloete I, Poel E. Generalized Hopfield networks with multiple stable states [J]. Neurocomputing, 1996, 13: 135–149
[64] Shankmukh K, Venkatesh Y V. Generalized scheme for optimal learning in recurrent neural networks [J]. Proc. Inst. Elect. Eng. Vision Image Signal Processing, 1995, 142: 71–77
[65] Nadal J P, Rau A. Storage capacity of potts-perceptron [J]. Journal de Physique Archives, 1991, 1:1109–1112 (in France)
[66] Tan S, Hao J, Vandewalle J. Determination of weights for Hopfield associative memory by error back propagation[C]. IEEE International Symposium on Circuits and Systems, 1991, 5: 2490-2494
[67] Schwarz S, Mathis W. Cellular neural network design with continuous signals[C]. Proc. 2nd Int. Workshop Cellular Neural Networks Applications, Munich, Germany, 1992, 17-22
[68] Meng X, Hu C. Using evolutionary programming to construct Hopfield neural networks[C]. IEEE International Conference on Intelligent Processing Systems, 1997, 1: 571-573
[69] Muezzinoglu M K, Guzelis C, Zurada J M. Construction of energy landscape for discrete Hopfield associative memory with guaranteed error correction capability[C]. First International IEEE EMBS Conference on Neural Engineering, 2003, 320- 323
[70] Zhang Z, Akiduki T, Imamura T, et al. Realization of multi-valued associative memory with cellular neural network [C]. IEEE International Conference on Systems, Man, and Cybernetics( SMC 2007), 2007, 1205-1210
[71] Zhang Z, Akiduki T, Miyake T, et al. Design of multivalued cellular neural networks for associative memory [C]. 2006 SICE-ICASE International Joint Conference, 2006,4057–4061
[72] Aoki H, Watanabe E, Nagata A. et al. Rotation-invariant image association for endoscopic positional identification using complex-valued associative memories [J]. Bio-inspired Applications of Connectionism, Lecture Notes in Computer Science, 2001, 2085: 369-374
[73] Aizenberg N N, Ivaskiv Y L. Multi-Valued Threshold Logic [M]. Naukova Dumka, Kiev, 1977 (in Russian).
[74] Aizenberg N N, Aizenberg I N. CNN based on multivalued neuron as a model of associative memory for gray-scale images [C]. CNNA92: Proc. 2nd Int. Workshop Cellular Neural Networks Applications, Munich, Germany, 1992: 36-41
[75] Shankmukh K, Venkatesh Y V. Generalized scheme for optimal learning in recurrent neural networks [C]. Proc. Inst. Elect. Eng. Vision Image Signal Processing, 1995, 142: 71–77
[76] Elizade E, Gomez S. Multistate perceptrons: learning rule and perceptron of maximal stability [J]. Journal of Physics A: Mathematical and Genera, 1992, 25:5039–5045
[77] Mertens S, Koehler H M, Bos S. Learning grey-toned patterns in neural networks [J]. Journal of Physics A: Mathematical and General, 1991, 24:4941–4952
[78] Si J, Michel A N. Analysis and synthesis of discrete-time neural networks with multilevel threshold functions[C] IEEE International Symposium on Circuits and Systems (ISCAS1991), 1991, 3: 1461–1464
[79] Yi Sun. Hopfield neural network based algorithms for image restoration and reconstruction Part I: algorithms and simulations. IEEE Trans. on Signal Processing, 2000, 48(7): 2105-2118
[80] Aizenberg I N, Aizenberg N N. Application of the neural networks based on multi-valued neurons in image processing and recognition [C]. SPIE Proceedings, 1998, 3307: 88-97
[81] Aizenberg I N, Aizenberg N N. Pattern recognition using neural network based on multi-valued neurons [J]. Lecture Notes in Computer Sciense, 1607-II (Mira J, Sanches-Andres J V Eds.), Springer-Verlag, 1999, 383-392
[82] Aizenberg N, Vandewalle J. Multi-valued and Universal Binary Neurons: Theory, Learning, Applications, Kluwer Academic Publishers, Boston/Dordrecht/London, 2000
[83] Aizenberg I, Aizenberg N, Butakoff C, et al. Image recognition on the neural network based on multi-valued neurons [C]. Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain, 2000, 2: 993-996
[84] Aoki H, Kosugi Y. An image storage system using complex-valued associative memory[C]. Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain 2000, 2: 626-629
[85] Aizenberg N N, Aizenberg I N, Krivosheev G A. Multi-valued neurons: mathematical model, networks, application to pattern recognition[C]. Proceeding of the 13th Conference on Pattern Recognition, Vienna, 1996, 185-189
[86] Lawrence S, Lee-Giles C, Chung-Tsoi A, Back A D. Face recognition: a convolutional neural-network approach [J]. IEEE Trans. on Neural Networks, 1997,8: 98-113
[87] Aizenberg I, Paliy D. A feedforward neural network based on multi-valued neurons.Computational Intelligence, Theory and Applications. Advances in Soft Computing, XIV, (B. Reusch - Ed.), Springer, Berlin, Heidelberg, New York, 2005, 599-612
[88] Aizenberg N N, Moraga C. Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm [J]. Soft Computing, 2007, 11(2): 169-183
[89] Aizenberg I, Butakoff C. Image processing using cellular neural networks based on multi-valued and universal binary neurons [J]. Journal of VLSI Signal Processing, 2002, 32: 169–188
[90] A.S. Miller, B.H. Blott, T.K. Hames, Review of neural network applications in medical imaging and signal processing. Medical and Biological Engineering and Computing, 1992, 449–464
[91] Aoki H, Kosugi Y. An image storage system using complex-valued associative memory. Proc. of the 15th International Conference on Pattern Recognition, Barcelona, 2000, 2: 626-629
[92] Aizenberg E, Myasnikova M S and Reinitz J. Temporal classification of drosophila segmentation gene expression patterns by the multi-valued neural [J]. Recognition Method Journal of Mathematical Biosciences (Elsevier), 2002, 176 (1): 155-159.
[93] Aizenberg T, Bregin C, Butakoff et al. Type of blur and blur parameters identification using neural network and its application to image restoration [J]. Lecture Notes in Computer Science, 2002, 2415: 1231-1236
[94]王麟琨,徐德,谭民.机器人视觉伺服研究进展[J].机器人, 2004, 26(3 ): 277-282
[95] Hutchinson S, Hager G D, Corke P I. A tutorial on visual servo control [J]. IEEE Trans. on Robotics and Automation, 1996, 12(5): 651-670
[96] Hashimoto K, Noritsugu T. Performance and sensitivity in visual servoing [C]. Proceedings of the 1998 IEEE International Conference on Robotics & Automation, Leuven, Belgium, 1998, 2321-2326
[97]田梦倩,罗翔.机器人视觉伺服系统结构及实现.制造业自动化. 2005. 27(12): 40-42
[98]席文明,罗翔,朱剑英.基于约束卡尔曼滤波器预测的视觉跟踪研究[J].南京航空航天大学学报, 2002, 34(6): 540-543
[99] Wei G Q, Hirzinger G. Multisensory visual servoing by a neural network [J]. IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics, 1999, 29(2): 276-280
[100]郭振民,陈善本,吴林.一种基于图像的无标定视觉伺服方法的研究[J].哈尔滨工业大学学报, 2002 34(3 ):294-296
[101]项龙江,司秉玉,薛定宇等.模型无关的无定标视觉伺服控制[J].机器人, 2003, 25(5): 424-427
[102] Hashimoto K,Kimoto T, Ebine T et al. Manipulator control with image-based visual servo[C]. Proceedings IEEE International Conference on Robotics and Automation, 1991, 3: 2267-2271
[103] Wasik Z, Saffiotti A. A fuzzy behavior-based control system for manipulation[C]. IEEE International Conference on Intelligent Robots and Systems, 2002, 2: 1596-1601
[104] Suh H I, Kim T W. Visual servoing algorithm using fuzzy logics and fuzzy-neural networks[C]. Proceedings IEEE International Conference on Robotics and Automation, 1996, 4: 3605-3612
[105] Wang H, Luo X, Zhu, J. 3-D visual tracking based on CMAC neural network and Kalman filter [J]. Journal of Southeast University (English Edition), 2003, 19(1):58-63
[106]于秀芬,段海滨,龚华军.基于时滞卡尔曼滤波的机器人视觉定位[J].电光与控制, 2004,11(2):29-31
[107] Qian J, Su J. Online estimation of image Jacobian matrix by Kalman-Bucy filter for uncalibrated stereo vision feedback [C]. Proceedings IEEE International Conference on Robotics and Automation, 2002, 1: 562-567
[108] Su, J. Performance analysis of neural network-based uncalibrated hand-eye coordination. Second International Symposium on Neural Networks. Proceedings, 2005, 222-227
[109]潘且鲁,苏剑波,席裕庚.基于神经网络的机器人手眼无标定平面视觉跟踪[J].自动化学报, 2001, 27(2): 194-199
[110]田梦倩,罗翔,黄惟一.视觉伺服机器人对运动目标操作的研究[J].机器人, 2003, 25(6): 546-552
[111]刘景泰,吴水华,孙雷等.基于视觉的遥操作机器人精密装配系统[J].机器人, 2005, 27(2): 178-182
[112] Emilio J. G, Sergio R C, Michael J S, et al. An efficient multi-camera, multi-target scheme for the three-dimensional control of robots using uncalibrated vision [J]. Robotics and Computer-Integrated Manufacturing, 2003, 19(5): 387-400
[113] Dhanesh R, Mandava R. Neural network-based robot visual positioning for intelligent assembly[J]. Journal of Intelligent Manufacturing, 2004, 15(2), 219-231
[114] Cupertino F, Giordano V, Mininno E et al. A neural visual servoing in uncalibrated environments for robotic manipulator[C]. 2004 IEEE International Conference on Systems, Man and Cybernetics, 2004: 5362-5367
[115] Suh H I, Kim T W. Fuzzy-neural-network-based visual feedback learning control for robot manipulators[C]. IEEE International Conference on Neural Networks, 1994, 5: 2781-2786
[116] Suh H I, Kim T W. Fuzzy membership function based neural networks with applications to the visual servoing of robot manipulators [J]. IEEE Trans. on Fuzzy Systems, 1994, 2(3): 203-220
[117] Yang Y X, Liu D, Liu H. Robot self-learning visual servoing algorithm using neural networks[C]. Proceedings of 2002 International Conference on Machine Learning and Cybernetics, 2002, 2: 739-742
[118] Chan C C, Lo E W. Visual servo control with artificial neural network[C]. Proceedings of the IEEE International Conference on Industrial Technology, 1994, 283-287
[119] Stanley K,Wu J,Gruver W A. A hybrid neural network based vision-guided robotic system [C]. Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS, 2001, 1: 322-327
[120] Kuhn D, Buessler J L, Urban J P. Neural approach to visual servoing for robotic hand eyecoordination[C]. IEEE International Conference on Neural Networks1995, 5: 2364-2369
[121] Garcia-Rodriguez R, Dean-Leon E, Parra-Vega V, et al. An adaptive neural network controller for visual tracking of constrained robot manipulators[C]. Proceedings of the 2005 American Control Conference, ACC, 2005, 5: 3694-3700
[122] Moreno-Armendariz M A., Yu W. A new fuzzy visual servoing with application to robot manipulator [C]. Proceedings of the 2005 American Control Conference, ACC, 2005, 5: 3688-3693
[123]席文明,朱剑英.基于分层神经网络带预测器的视觉跟踪[J].西安交通大学学报. 2002, 36(7): 740-743
[124] Jiang P, Li Z, Chen Y. Iterative learning neural network control for robot learning from demonstration [J].控制理论与应用. 2004, 21(3): 447-452
[125] Hashimoto H, Kubota T, Sato Motoo, et al. Visual control of robotic manipulator based on neural networks [J]. IEEE Trans. on Industrial Electronics, 1992, 39(6): 490-496
[126] Hashimoto H, Kubota T, Kudou M, et al. Self-organizing visual servo system based on neural networks [J]. IEEE Control Systems Magazine, 1992, 12(2): 31-36
[127] Miller T W. Sensor-based control of robotic manipulators using a general learning algorithm [J]. IEEE Journal of Robotics and Automation. 1987, 3(2): 157-165
[128]罗家洪.矩阵分析引论[M].广州:华南理工大学出版社, 1998
[129]廖晓昕.稳定性的数学理论及应用[M].武汉:华中师范大学出版社, 2001
[130] Cao J, Wang J. Global asymptotic stability of a general class of recurrent neural networks with time-varying delays [J]. IEEE Trans. on Circuits and Systems I, 2003, 50(1):34-44
[131] Zhang J Y. Globally exponential stability of neural networks with variable delays. IEEE Trans. on Circuits and Systems, 2003, 50(3): 288-290
[132] Boyd S, Ghaoui L E, Feron E, et al. Linear Matrix Inequalities in System and Control Theory. PA:SIAM,Philadelphia, 1994
[133] Liao X F, Chen G, Sanchez E N. Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach [J]. Neural Networks, 2002, 15(7): 855-866
[134] Khall H K. Nonlinear systems (Third Edition) [M]. Prentice Hall, 2002
[135]徐军.递归神经网络稳定性分析[D].浙江大学博士学位论文, 2007
[136]王耀南.智能信息处理技术[M].北京:高等教育出版社, 2003
[137]飞思科技产品研发中心编著.神经网络理论与MATLAB7实现[M].北京:电子工业出版社, 2005
[138]周政. BP神经网络的发展现状综述[J].山西电子技术, 2008(2): 90-92
[139]鲁娟娟,陈红. BP神经网络的研究进展[J].控制工程, 2006, 13(5): 449-456
[140]冈萨雷斯.数字图像处理(第二版)[M].阮秋琦,阮宇智等译.北京:电子工业出版, 2003
[141]朱秀昌,刘峰,胡栋.数字图像处理与图像通信[M].北京:北京邮电大学出版社, 2002
[142]潘梅森.基于神经网络的降质图像恢复研究[D].华中科技大学硕士学位论文, 2005
[143]李颖.基于多神经网络分类器的军事目标识别方法研究[J].沈阳理工大学学报, 2005, 24(4): 18-22
[144]韩彦芳,施鹏飞.基于数字图像处理的表面缺损检测[J].技术测控技术, 2005, 24(9): 15-18
[145]田明辉,万寿红,岳丽华.遥感图像中复杂海面背景下的海上舰船检测[J].小型微型计算机系统, 2008(11): 2162-2166
[146]何春香,刘泊,小波BP神经网络在零件识别应用中的研究[J].哈尔滨理工大学学报, 2008, 13(5): 50-53
[147]袁佳,郭建钢.车辆牌照图像识别技术研究进展[J].机电技术, 2008(1): 77-79
[148]刘理华,白鹏飞,徐勇.遥感图像中港口水域的检测方法[J].舰船电子工程, 2008, 28(9): 37-39
[149]陈元琰,姜颖军.基于计算机视觉的玻璃瓶裂纹在线检测系统[J].计算机应用, 2001, 21 (11) : 48 - 49.
[150]熊有伦.机器人学[M].北京:机械工业出版社,1993
[151]蔡自兴.机器人学的发展趋势和发展战略[M].机器人技术与应用, 2001,(4): 11-16
[152] KLD-600六自由度教学机器人使用手册[M].哈尔滨科利达智能控制技术有限公司
[153] Rajati M R, Menhaj M B. On classification of some Hopfield-type learning rules via stability measures[C]. International Conference 9th Fuzzy Days in Dortmund, Germany, 2006 Proceedings, 2006, 75-83
[154] Harris C, Stephens M. A combined corner and edge detector[C]. Proceedings of 4th Vision Conference. 1988, 147-151
[155] Michel A N, Farrell J A, Sun H F. Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memory [J]. IEEE Trans. on Circuit and Systems, 1990, 37(11): 1356-1366
[156] Li J H, Michel A N, Forod W. Qualitative analysis and synthesis of a class of neural networks. IEEE Trans. on Circuit and Systems, 1988, 35(8): 976-986
[157] Aoki H, Azimi-Sadjadi M R, Kosugi Y. Image associateon using a complex-valued associateive memory model[J]. IEICE Trans. on Fundamentals of Electroncs, Communications and Computer Sciences. 2001, e83A(9):1824-1832
[158]范翠翠.图像角点检测方法的研究[J].青岛大学硕士学位论文, 2008
[159]陈乐,吕文阁,丁少华.角点检测技术研究进展[J].自动化技术与应用,2005,24(5):1-5
[160]马颂德,张正有.计算机视觉[M].北京:科学出版社,1998
[2]赵清杰,连广宇.机器人视觉伺服综述[J].控制与决策, 2001,16(6): 849-853
[3]李新.面向神经计算的视觉信息处理研究[D].西北工业大学博士学位论文. 2002
[4]王丹青,李志俊.基于神经网络的工业图像识别[J].武汉科技大学学报(自然科学版) , 2005, 28(4): 387-390
[5] Costantini G, Casali D, Perfetti R. Neural associative memory storing gray-coded gray-scale images [J]. IEEE Trans. on Neural Networks, 2003, 14(3): 703-707
[6] Aizenberg I, Butakoff C. Neural network based on multi-valued neurons and its applications to image recognition and blur recognition[C]. Proc. SPIE - The International Society for Optical Engineering, 2001, 4305: 11-21,
[7] Hirose A. Complex-valued neural networks: theories and applications [M]. World Scientific Series on Innovation Intelligence, vol 5, Singapore: World Scientific Publishing Co. Pte. Ltd. 2003
[8] Hideki H, Takashi K, Motoo S, et al. Visual control of robotic manipulator based on neural networks. IEEE Trans. on Industrial Electronics, 1992, 39(6): 490-496
[9]林靖,陈辉堂.机器人视觉伺服系统的研究[J].控制理论与应用, 2000, 17(4):476-481
[10]焦李成.神经网络系统理论[M ].西安:西安电子科技大学出版社, 1991
[11]何玉彬,李新忠.神经网络控制及其应用[M ].北京:科学出版社, 2000
[12] McCulloch W S, Pitts W A. A logical calculus of the ideas immanent in nervous activity [J]. Bulletin of Mathematical Biophysics, 1943, 5: 115-133
[13] Hebb D O. The Organization of Behavious [M]. New York, John Wiley & Sons Inc., 1949
[14] Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain [J]. Psychology Review, 1958, 65: 386-408
[15] Minsky M, Papert S. Perceptron [M]. Cambridge, MA: MIT Press, 1969
[16] Hopfield J J. Neural networks and physical systems with emergent collective computational abilities[C]. Proceeding of the National Academy of Science. USA (Biophysics), 1982, 79: 2554-2558
[17] Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons[C]. Proceedins of the National Academy of Science, USA(Biophysics), 1984, 81:3088-3092
[18] Chua L O and Yang L. Cellular neural networks: theory [J]. IEEE Trans. on Circuits and Systems, 1988, 35:1257-1272
[19]徐立中,刘富强.基于模型的工业图像增强技术[J].仪器仪表学报, 1999, 20(6):609-611
[20]黎明,严超华,刘高航.基于前向神经网络和Hopfield反馈神经网络的边界检测法[J].中国图象图形学报. 1999, 4 (8): 663-667
[21] Chao C H, Dhawan A P. Edge detection using a Hopfield neural network [J]. Optical Engineering, 1994(33): 3739-3747
[22] Qiu G, Varley M R, Terrell T J. Improved block truncation coding using Hopfield neural network[J]. Electronics Letters, 1991, 27 (21): 1924-1926
[23]马向玲,田宝国. Hopfield网络应用实例分析[J].计算机仿真, 2003, 20(8): 64-66
[24]张敏瑞,张丽娜,黄兴.基于神经网络自联想的数字图像水印算法[J].江西师范大学学报(自然科学版) , 2007, 31(5): 445-449
[25]王宇,何小祥.改进的网络图像复原[J].计算机工程, 2007, 33(17): 54-57
[26]李云栋,张其善.基于联想记忆的彩色图像自适应预测编码方法[J].信号处理, 2006, 22(2): 137-140
[27]周日贵,姜楠,丁秋林.量子Hopfield神经网络及图像识别[J].中国图象图形学报, 2008,13(1): 119-123
[28]吴锡生,王士同.模糊形态联想记忆网络及其在细胞图像联想识别中的应用[J].中国图象图形学报, 2006, 11(10): 1450-1455
[29]叶旭,李志能,陈抗生.基于矢量量化及Hopfield模型的灰度级图像识别[J].光学学报, 1998, 18: 112-115
[30] Widrow B, McCool J, Ball M. The complex LMS algorithm [C]. Proc. IEEE, 1975, 63(4): 719–720
[31] Georgiou, G M, Koutsougeras, C. Complex domain backpropagation [J]. IEEE Trans. on Circuits and Systems II: Analog and Digital Signal Processing, 1992, 39(5): 330-334
[32] Aizenberg N N, Ivaskiv Y L, Pospelov D A. About one generalization of the threshold function [J]. Doklady Akademii Nauk SSSR (The Reports of the Academy of Sciences of the USSR), 1971, 196(6): 1287-1290 (in Russian)
[33] Aizenberg I, Paliy D, Astola J T. Multilayer neural network based on multi-valued neurons and the blur identification problem [C]. 2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006, 473-479
[34]钟守铭,刘碧森,王晓梅等.神经网络稳定性理论[M].北京:科学出版, 2008
[35]廖晓昕.动力系统的稳定性理论和应用[M].北京:国防工业出版社, 2000
[36] Kuroe Y, Hashimoto N, Mori T. On energy function for complex-valued neural networks and its applications[C]. Proceedings of the 9th International Conference on Neural Information Processing (ICONIP'02) , 2002, 3:1079-1083
[37] Special session on“Complex-valued neural networks and their applications”in Knowledge-Based Intelligent Information Engineering System & Allied Technologies, KES2001, Part 1, 10s Press, Tokyo, 2001, 550-580
[38] Kuroe Y, Yoshida M, Mori T. On Activation functions for complex-Valued neuralnetworks–existence of energy functions[C]. International Conference on Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP 2003), 2003, 985–992
[39] Mishra D, Tolambiya A, Shukla A, et al. Stability analysis for higher order complex-valued Hopfield neural network[C]. Proceedings of the 13th International Conference on Neural Information Processing (ICONIP'06) Part I, LNCS 4232, 2006, 608–615
[40] Kuroe Y, Taniguchi Y. Models of self-correlation type complex-valued associative memories and their dynamics[C]. International Conference on Artificial Neural Networks (ICANN 2005), LNCS 3696, 2005, 185-192
[41] Kuroe Y, Taniguchi Y. Models of self-correlation type complex-valued associative memories and their performance comparison[C]. 2006 International Joint Conference on Neural Networks, Vancouver, BC, Canada July 16-21, 2006, 213-217
[42] Hirose A. Dynamics of fully complex-valued neural networks [J]. Electronics Letters, 1992, 28(16): 1492-1494
[43] Kuroe Y, Hashimoto N, Mori T. Qualitative analysis of a self-correlation type complex valued associative memories [J]. Nonlinear Analysis, 2001, 47(9):5795-5806
[44] Kuroe Y, Hashimoto N, Mori T. Qualitative analysis of continuous complex-valued associative memories[C]. International Conference on Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP 2001), 2001, 843 -850
[45] Lee D L. Relaxation of the stability condition of the complex-valued neural networks[J] . IEEE Trans. on Neural Networks, 2001, 12(5): 1260-1262
[46] Lee D L. Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule [J]. IEEE Trans. on Neural Networks, 2001, 12(2): 439–443
[47] Lee D L. New stability conditions for Hopfield networks in partial simultaneous update model [J]. IEEE Trans. on Neural Networks, 1999, 10(4): 975–978
[48] Xu Z B, Kwong C P. Global convergence and asymptotic stability of asymmetric Hopfield networks [J]. Journal of Mathematical Analysis and Applications, 1995,191(3): 405–427
[49] Xu Z B, Hu G Q, Kwong C P. Asymmetric Hopfield networks: theory and applications [J]. Neural Networks, 1996, 9(3): 483–501
[50] Vidyasagar M. Location and stability of the high-gain equilibria of nonlinear neural networks [J]. IEEE Trans. on Neural Networks, 1993, 4(4): 660–672
[51] Morita M. Memory and learning of sequential patterns by nonmonotone neural networks [J]. Neural Networks, 1996, 9(8): 1477–1489
[52] Hirose A. Continuous complex-valued back-propagation learning [J]. Electronics Letters, 1992, 28(20): 1854–1855
[53] Hirose A. Proposal of fully complex-valued neural networks[C]. International Joint Conference on Neural Networks(IJCNN1992), 1992, 4: 152–157
[54] Hirose A, Onishi H. Proposal of relative-minimization learning for behavior stabilization of complex-valued recurrent neural networks [J]. Neurocomputing, 1999, 24: 163-171
[55] Benvenuto N, Piazza F. On the complex backpropagation algorithm [J]. IEEE Trans. on Signal Processing, 1992,40(4): 967–969
[56] Hanna A I, Mandic D P. A fully adaptive normalized nonlinear gradient descent algorithm for complex-valued nonlinear adaptive filters [J]. IEEE Trans. on signal processing, 2003, 51(10): 2540-2549
[57] Chen X M, Zheng T, Variappan C. A modified error backpropagation algorithm for complex-value neural networks [J]. International Journal of Neural Systems, 2005, 15( 6): 435–443
[58] Personnaz L, Guyon I, Dreyfus G. Collective computational properties of neural networks: New learning mechanisms [J]. Physical Review Online Archive, 1986, A34: 4217–4228
[59] Personnaz L, Guyon I, Dreyfus G, et al. A biologically constrained learning mechanism in networks of formal neurons[J], Journal of Statistical Physics,1986, 43(3-4): 411–422
[60] Jankowski S, Lozowski A, Zurada J M. Complex-valued multistate neural associative memory [J]. IEEE Trans. Neural Networks, 1996, 7(6): 1491–1496
[61] Lee D L. Improvements of complex-valued Hopfield associative memory by using generalized projection rules [J]. IEEE Trans. on Neural Networks, 2006, 17(5): 1341-1347
[62] Muezzinoglu M K, Guzelis C, Zurada J M. A new design method for the complex-valued multistate Hopfield associative memory [J]. IEEE Trans. on Neural Networks, 2003, 14(4): 891–899
[63] Zurada J M, Cloete I, Poel E. Generalized Hopfield networks with multiple stable states [J]. Neurocomputing, 1996, 13: 135–149
[64] Shankmukh K, Venkatesh Y V. Generalized scheme for optimal learning in recurrent neural networks [J]. Proc. Inst. Elect. Eng. Vision Image Signal Processing, 1995, 142: 71–77
[65] Nadal J P, Rau A. Storage capacity of potts-perceptron [J]. Journal de Physique Archives, 1991, 1:1109–1112 (in France)
[66] Tan S, Hao J, Vandewalle J. Determination of weights for Hopfield associative memory by error back propagation[C]. IEEE International Symposium on Circuits and Systems, 1991, 5: 2490-2494
[67] Schwarz S, Mathis W. Cellular neural network design with continuous signals[C]. Proc. 2nd Int. Workshop Cellular Neural Networks Applications, Munich, Germany, 1992, 17-22
[68] Meng X, Hu C. Using evolutionary programming to construct Hopfield neural networks[C]. IEEE International Conference on Intelligent Processing Systems, 1997, 1: 571-573
[69] Muezzinoglu M K, Guzelis C, Zurada J M. Construction of energy landscape for discrete Hopfield associative memory with guaranteed error correction capability[C]. First International IEEE EMBS Conference on Neural Engineering, 2003, 320- 323
[70] Zhang Z, Akiduki T, Imamura T, et al. Realization of multi-valued associative memory with cellular neural network [C]. IEEE International Conference on Systems, Man, and Cybernetics( SMC 2007), 2007, 1205-1210
[71] Zhang Z, Akiduki T, Miyake T, et al. Design of multivalued cellular neural networks for associative memory [C]. 2006 SICE-ICASE International Joint Conference, 2006,4057–4061
[72] Aoki H, Watanabe E, Nagata A. et al. Rotation-invariant image association for endoscopic positional identification using complex-valued associative memories [J]. Bio-inspired Applications of Connectionism, Lecture Notes in Computer Science, 2001, 2085: 369-374
[73] Aizenberg N N, Ivaskiv Y L. Multi-Valued Threshold Logic [M]. Naukova Dumka, Kiev, 1977 (in Russian).
[74] Aizenberg N N, Aizenberg I N. CNN based on multivalued neuron as a model of associative memory for gray-scale images [C]. CNNA92: Proc. 2nd Int. Workshop Cellular Neural Networks Applications, Munich, Germany, 1992: 36-41
[75] Shankmukh K, Venkatesh Y V. Generalized scheme for optimal learning in recurrent neural networks [C]. Proc. Inst. Elect. Eng. Vision Image Signal Processing, 1995, 142: 71–77
[76] Elizade E, Gomez S. Multistate perceptrons: learning rule and perceptron of maximal stability [J]. Journal of Physics A: Mathematical and Genera, 1992, 25:5039–5045
[77] Mertens S, Koehler H M, Bos S. Learning grey-toned patterns in neural networks [J]. Journal of Physics A: Mathematical and General, 1991, 24:4941–4952
[78] Si J, Michel A N. Analysis and synthesis of discrete-time neural networks with multilevel threshold functions[C] IEEE International Symposium on Circuits and Systems (ISCAS1991), 1991, 3: 1461–1464
[79] Yi Sun. Hopfield neural network based algorithms for image restoration and reconstruction Part I: algorithms and simulations. IEEE Trans. on Signal Processing, 2000, 48(7): 2105-2118
[80] Aizenberg I N, Aizenberg N N. Application of the neural networks based on multi-valued neurons in image processing and recognition [C]. SPIE Proceedings, 1998, 3307: 88-97
[81] Aizenberg I N, Aizenberg N N. Pattern recognition using neural network based on multi-valued neurons [J]. Lecture Notes in Computer Sciense, 1607-II (Mira J, Sanches-Andres J V Eds.), Springer-Verlag, 1999, 383-392
[82] Aizenberg N, Vandewalle J. Multi-valued and Universal Binary Neurons: Theory, Learning, Applications, Kluwer Academic Publishers, Boston/Dordrecht/London, 2000
[83] Aizenberg I, Aizenberg N, Butakoff C, et al. Image recognition on the neural network based on multi-valued neurons [C]. Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain, 2000, 2: 993-996
[84] Aoki H, Kosugi Y. An image storage system using complex-valued associative memory[C]. Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain 2000, 2: 626-629
[85] Aizenberg N N, Aizenberg I N, Krivosheev G A. Multi-valued neurons: mathematical model, networks, application to pattern recognition[C]. Proceeding of the 13th Conference on Pattern Recognition, Vienna, 1996, 185-189
[86] Lawrence S, Lee-Giles C, Chung-Tsoi A, Back A D. Face recognition: a convolutional neural-network approach [J]. IEEE Trans. on Neural Networks, 1997,8: 98-113
[87] Aizenberg I, Paliy D. A feedforward neural network based on multi-valued neurons.Computational Intelligence, Theory and Applications. Advances in Soft Computing, XIV, (B. Reusch - Ed.), Springer, Berlin, Heidelberg, New York, 2005, 599-612
[88] Aizenberg N N, Moraga C. Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm [J]. Soft Computing, 2007, 11(2): 169-183
[89] Aizenberg I, Butakoff C. Image processing using cellular neural networks based on multi-valued and universal binary neurons [J]. Journal of VLSI Signal Processing, 2002, 32: 169–188
[90] A.S. Miller, B.H. Blott, T.K. Hames, Review of neural network applications in medical imaging and signal processing. Medical and Biological Engineering and Computing, 1992, 449–464
[91] Aoki H, Kosugi Y. An image storage system using complex-valued associative memory. Proc. of the 15th International Conference on Pattern Recognition, Barcelona, 2000, 2: 626-629
[92] Aizenberg E, Myasnikova M S and Reinitz J. Temporal classification of drosophila segmentation gene expression patterns by the multi-valued neural [J]. Recognition Method Journal of Mathematical Biosciences (Elsevier), 2002, 176 (1): 155-159.
[93] Aizenberg T, Bregin C, Butakoff et al. Type of blur and blur parameters identification using neural network and its application to image restoration [J]. Lecture Notes in Computer Science, 2002, 2415: 1231-1236
[94]王麟琨,徐德,谭民.机器人视觉伺服研究进展[J].机器人, 2004, 26(3 ): 277-282
[95] Hutchinson S, Hager G D, Corke P I. A tutorial on visual servo control [J]. IEEE Trans. on Robotics and Automation, 1996, 12(5): 651-670
[96] Hashimoto K, Noritsugu T. Performance and sensitivity in visual servoing [C]. Proceedings of the 1998 IEEE International Conference on Robotics & Automation, Leuven, Belgium, 1998, 2321-2326
[97]田梦倩,罗翔.机器人视觉伺服系统结构及实现.制造业自动化. 2005. 27(12): 40-42
[98]席文明,罗翔,朱剑英.基于约束卡尔曼滤波器预测的视觉跟踪研究[J].南京航空航天大学学报, 2002, 34(6): 540-543
[99] Wei G Q, Hirzinger G. Multisensory visual servoing by a neural network [J]. IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics, 1999, 29(2): 276-280
[100]郭振民,陈善本,吴林.一种基于图像的无标定视觉伺服方法的研究[J].哈尔滨工业大学学报, 2002 34(3 ):294-296
[101]项龙江,司秉玉,薛定宇等.模型无关的无定标视觉伺服控制[J].机器人, 2003, 25(5): 424-427
[102] Hashimoto K,Kimoto T, Ebine T et al. Manipulator control with image-based visual servo[C]. Proceedings IEEE International Conference on Robotics and Automation, 1991, 3: 2267-2271
[103] Wasik Z, Saffiotti A. A fuzzy behavior-based control system for manipulation[C]. IEEE International Conference on Intelligent Robots and Systems, 2002, 2: 1596-1601
[104] Suh H I, Kim T W. Visual servoing algorithm using fuzzy logics and fuzzy-neural networks[C]. Proceedings IEEE International Conference on Robotics and Automation, 1996, 4: 3605-3612
[105] Wang H, Luo X, Zhu, J. 3-D visual tracking based on CMAC neural network and Kalman filter [J]. Journal of Southeast University (English Edition), 2003, 19(1):58-63
[106]于秀芬,段海滨,龚华军.基于时滞卡尔曼滤波的机器人视觉定位[J].电光与控制, 2004,11(2):29-31
[107] Qian J, Su J. Online estimation of image Jacobian matrix by Kalman-Bucy filter for uncalibrated stereo vision feedback [C]. Proceedings IEEE International Conference on Robotics and Automation, 2002, 1: 562-567
[108] Su, J. Performance analysis of neural network-based uncalibrated hand-eye coordination. Second International Symposium on Neural Networks. Proceedings, 2005, 222-227
[109]潘且鲁,苏剑波,席裕庚.基于神经网络的机器人手眼无标定平面视觉跟踪[J].自动化学报, 2001, 27(2): 194-199
[110]田梦倩,罗翔,黄惟一.视觉伺服机器人对运动目标操作的研究[J].机器人, 2003, 25(6): 546-552
[111]刘景泰,吴水华,孙雷等.基于视觉的遥操作机器人精密装配系统[J].机器人, 2005, 27(2): 178-182
[112] Emilio J. G, Sergio R C, Michael J S, et al. An efficient multi-camera, multi-target scheme for the three-dimensional control of robots using uncalibrated vision [J]. Robotics and Computer-Integrated Manufacturing, 2003, 19(5): 387-400
[113] Dhanesh R, Mandava R. Neural network-based robot visual positioning for intelligent assembly[J]. Journal of Intelligent Manufacturing, 2004, 15(2), 219-231
[114] Cupertino F, Giordano V, Mininno E et al. A neural visual servoing in uncalibrated environments for robotic manipulator[C]. 2004 IEEE International Conference on Systems, Man and Cybernetics, 2004: 5362-5367
[115] Suh H I, Kim T W. Fuzzy-neural-network-based visual feedback learning control for robot manipulators[C]. IEEE International Conference on Neural Networks, 1994, 5: 2781-2786
[116] Suh H I, Kim T W. Fuzzy membership function based neural networks with applications to the visual servoing of robot manipulators [J]. IEEE Trans. on Fuzzy Systems, 1994, 2(3): 203-220
[117] Yang Y X, Liu D, Liu H. Robot self-learning visual servoing algorithm using neural networks[C]. Proceedings of 2002 International Conference on Machine Learning and Cybernetics, 2002, 2: 739-742
[118] Chan C C, Lo E W. Visual servo control with artificial neural network[C]. Proceedings of the IEEE International Conference on Industrial Technology, 1994, 283-287
[119] Stanley K,Wu J,Gruver W A. A hybrid neural network based vision-guided robotic system [C]. Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS, 2001, 1: 322-327
[120] Kuhn D, Buessler J L, Urban J P. Neural approach to visual servoing for robotic hand eyecoordination[C]. IEEE International Conference on Neural Networks1995, 5: 2364-2369
[121] Garcia-Rodriguez R, Dean-Leon E, Parra-Vega V, et al. An adaptive neural network controller for visual tracking of constrained robot manipulators[C]. Proceedings of the 2005 American Control Conference, ACC, 2005, 5: 3694-3700
[122] Moreno-Armendariz M A., Yu W. A new fuzzy visual servoing with application to robot manipulator [C]. Proceedings of the 2005 American Control Conference, ACC, 2005, 5: 3688-3693
[123]席文明,朱剑英.基于分层神经网络带预测器的视觉跟踪[J].西安交通大学学报. 2002, 36(7): 740-743
[124] Jiang P, Li Z, Chen Y. Iterative learning neural network control for robot learning from demonstration [J].控制理论与应用. 2004, 21(3): 447-452
[125] Hashimoto H, Kubota T, Sato Motoo, et al. Visual control of robotic manipulator based on neural networks [J]. IEEE Trans. on Industrial Electronics, 1992, 39(6): 490-496
[126] Hashimoto H, Kubota T, Kudou M, et al. Self-organizing visual servo system based on neural networks [J]. IEEE Control Systems Magazine, 1992, 12(2): 31-36
[127] Miller T W. Sensor-based control of robotic manipulators using a general learning algorithm [J]. IEEE Journal of Robotics and Automation. 1987, 3(2): 157-165
[128]罗家洪.矩阵分析引论[M].广州:华南理工大学出版社, 1998
[129]廖晓昕.稳定性的数学理论及应用[M].武汉:华中师范大学出版社, 2001
[130] Cao J, Wang J. Global asymptotic stability of a general class of recurrent neural networks with time-varying delays [J]. IEEE Trans. on Circuits and Systems I, 2003, 50(1):34-44
[131] Zhang J Y. Globally exponential stability of neural networks with variable delays. IEEE Trans. on Circuits and Systems, 2003, 50(3): 288-290
[132] Boyd S, Ghaoui L E, Feron E, et al. Linear Matrix Inequalities in System and Control Theory. PA:SIAM,Philadelphia, 1994
[133] Liao X F, Chen G, Sanchez E N. Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach [J]. Neural Networks, 2002, 15(7): 855-866
[134] Khall H K. Nonlinear systems (Third Edition) [M]. Prentice Hall, 2002
[135]徐军.递归神经网络稳定性分析[D].浙江大学博士学位论文, 2007
[136]王耀南.智能信息处理技术[M].北京:高等教育出版社, 2003
[137]飞思科技产品研发中心编著.神经网络理论与MATLAB7实现[M].北京:电子工业出版社, 2005
[138]周政. BP神经网络的发展现状综述[J].山西电子技术, 2008(2): 90-92
[139]鲁娟娟,陈红. BP神经网络的研究进展[J].控制工程, 2006, 13(5): 449-456
[140]冈萨雷斯.数字图像处理(第二版)[M].阮秋琦,阮宇智等译.北京:电子工业出版, 2003
[141]朱秀昌,刘峰,胡栋.数字图像处理与图像通信[M].北京:北京邮电大学出版社, 2002
[142]潘梅森.基于神经网络的降质图像恢复研究[D].华中科技大学硕士学位论文, 2005
[143]李颖.基于多神经网络分类器的军事目标识别方法研究[J].沈阳理工大学学报, 2005, 24(4): 18-22
[144]韩彦芳,施鹏飞.基于数字图像处理的表面缺损检测[J].技术测控技术, 2005, 24(9): 15-18
[145]田明辉,万寿红,岳丽华.遥感图像中复杂海面背景下的海上舰船检测[J].小型微型计算机系统, 2008(11): 2162-2166
[146]何春香,刘泊,小波BP神经网络在零件识别应用中的研究[J].哈尔滨理工大学学报, 2008, 13(5): 50-53
[147]袁佳,郭建钢.车辆牌照图像识别技术研究进展[J].机电技术, 2008(1): 77-79
[148]刘理华,白鹏飞,徐勇.遥感图像中港口水域的检测方法[J].舰船电子工程, 2008, 28(9): 37-39
[149]陈元琰,姜颖军.基于计算机视觉的玻璃瓶裂纹在线检测系统[J].计算机应用, 2001, 21 (11) : 48 - 49.
[150]熊有伦.机器人学[M].北京:机械工业出版社,1993
[151]蔡自兴.机器人学的发展趋势和发展战略[M].机器人技术与应用, 2001,(4): 11-16
[152] KLD-600六自由度教学机器人使用手册[M].哈尔滨科利达智能控制技术有限公司
[153] Rajati M R, Menhaj M B. On classification of some Hopfield-type learning rules via stability measures[C]. International Conference 9th Fuzzy Days in Dortmund, Germany, 2006 Proceedings, 2006, 75-83
[154] Harris C, Stephens M. A combined corner and edge detector[C]. Proceedings of 4th Vision Conference. 1988, 147-151
[155] Michel A N, Farrell J A, Sun H F. Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memory [J]. IEEE Trans. on Circuit and Systems, 1990, 37(11): 1356-1366
[156] Li J H, Michel A N, Forod W. Qualitative analysis and synthesis of a class of neural networks. IEEE Trans. on Circuit and Systems, 1988, 35(8): 976-986
[157] Aoki H, Azimi-Sadjadi M R, Kosugi Y. Image associateon using a complex-valued associateive memory model[J]. IEICE Trans. on Fundamentals of Electroncs, Communications and Computer Sciences. 2001, e83A(9):1824-1832
[158]范翠翠.图像角点检测方法的研究[J].青岛大学硕士学位论文, 2008
[159]陈乐,吕文阁,丁少华.角点检测技术研究进展[J].自动化技术与应用,2005,24(5):1-5
[160]马颂德,张正有.计算机视觉[M].北京:科学出版社,1998