神经网络图像压缩算法的FPGA实现技术研究
|
摘要
神经网络图像压缩是图像压缩和神经网络领域的主要研究方向之一,基于多层前馈神经网络的压缩算法在神经网络压缩算法中最有代表性。本文结合国家某科研项目对该类算法的硬件实现进行研究,具有重要的理论和实用价值。
本文重点研究用FPGA(现场可编程门阵列)实现神经网络图像压缩的技术问题,论文提出了一种用FPGA实现图像压缩算法的技术方案,并提出该方案中重要模块的设计方案,详细给出了设计思路、模块结构及硬件时序仿真结果。
本文首先介绍了神经网络图像压缩的现状,研究了三层前馈神经网络理论以及BP算法。给出了基于三层前馈式BP网络的图像压缩及解压缩算法,选择合适的传输函数,使用一些图像对神经网络进行了训练,得出网络的重要参数,完成了针对图像压缩的BP网络设计。
其次,本文针对给出的基于三层前馈式BP神经网络的图像压缩及解压缩算法,对主要的硬件实现方案进行了对比,论证了使用FPGA实现的优点,提出了一种用FPGA实现图像压缩算法的技术方案。然后,对FPGA实现方案中的主要模块的电路设计思路和设计结构进行了研究,提出了针对通用设计方法的相应改进,给出了时序仿真波形图及图像压缩算法的FPGA电路原理图。
最后,分析和硬件仿真结果表明,本文所提出的基于FPGA的神经网络压缩方案合理可行,具有一定先进性和实用性,对相关研究工作具有重要参考价值。
Neural network image compression is one of the major research directions in the fields of image compression and neural network. The compression algorithm based on multilayer feedforward neural network is the most representative one in the neural network compression algorithms. Supported by a national scientific project, this thesis researches on a hardware implementation of such algorithms, it has a great theoretical and practical value.
This thesis mainly investigates the technical questions in implementing this neural network image compression with FPGA (Field Programmable Gate Array),proposes a technology solution of implementing a neural network image compression with FPGA, and designs the key modules in the solution. It also gives the details of the design idea, the module structure and the hardware timing simulation results.
Firstly, this thesis introduces present status of neural network image compression, studies the theories of three-layer feedforward and BP algorithm. It gives the image compression and decompression algorithm based on three-layer feedforward BP network, chooses proper transmission function and trains the neural network with some images. At last, the article gets the key parameters of the network to finish the BP network design for image compression.
Secondly, this article compares the major hardware solution according to the image compression and decompression algorithm based on three-layer feedforward BP network. It demonstrates the advantages of implementing with FPGA and presents a technical solution of implementing image compression algorithm with FPGA. Then, the thesis studies the circuit design ideas and design structure of the key modules in the solution with FPGA,it puts forward the corresponding improvements according to universal design method, gives the timing simulation waveforms and the FPGA schematic diagram of image compression algorithm.
Finally,the analysis and hardware simulation results show that the neural network compression solution with FPGA in this thesis is realizable, practical and advanced. It has an important reference value to relevant study works.
本文重点研究用FPGA(现场可编程门阵列)实现神经网络图像压缩的技术问题,论文提出了一种用FPGA实现图像压缩算法的技术方案,并提出该方案中重要模块的设计方案,详细给出了设计思路、模块结构及硬件时序仿真结果。
本文首先介绍了神经网络图像压缩的现状,研究了三层前馈神经网络理论以及BP算法。给出了基于三层前馈式BP网络的图像压缩及解压缩算法,选择合适的传输函数,使用一些图像对神经网络进行了训练,得出网络的重要参数,完成了针对图像压缩的BP网络设计。
其次,本文针对给出的基于三层前馈式BP神经网络的图像压缩及解压缩算法,对主要的硬件实现方案进行了对比,论证了使用FPGA实现的优点,提出了一种用FPGA实现图像压缩算法的技术方案。然后,对FPGA实现方案中的主要模块的电路设计思路和设计结构进行了研究,提出了针对通用设计方法的相应改进,给出了时序仿真波形图及图像压缩算法的FPGA电路原理图。
最后,分析和硬件仿真结果表明,本文所提出的基于FPGA的神经网络压缩方案合理可行,具有一定先进性和实用性,对相关研究工作具有重要参考价值。
Neural network image compression is one of the major research directions in the fields of image compression and neural network. The compression algorithm based on multilayer feedforward neural network is the most representative one in the neural network compression algorithms. Supported by a national scientific project, this thesis researches on a hardware implementation of such algorithms, it has a great theoretical and practical value.
This thesis mainly investigates the technical questions in implementing this neural network image compression with FPGA (Field Programmable Gate Array),proposes a technology solution of implementing a neural network image compression with FPGA, and designs the key modules in the solution. It also gives the details of the design idea, the module structure and the hardware timing simulation results.
Firstly, this thesis introduces present status of neural network image compression, studies the theories of three-layer feedforward and BP algorithm. It gives the image compression and decompression algorithm based on three-layer feedforward BP network, chooses proper transmission function and trains the neural network with some images. At last, the article gets the key parameters of the network to finish the BP network design for image compression.
Secondly, this article compares the major hardware solution according to the image compression and decompression algorithm based on three-layer feedforward BP network. It demonstrates the advantages of implementing with FPGA and presents a technical solution of implementing image compression algorithm with FPGA. Then, the thesis studies the circuit design ideas and design structure of the key modules in the solution with FPGA,it puts forward the corresponding improvements according to universal design method, gives the timing simulation waveforms and the FPGA schematic diagram of image compression algorithm.
Finally,the analysis and hardware simulation results show that the neural network compression solution with FPGA in this thesis is realizable, practical and advanced. It has an important reference value to relevant study works.
引文
[1]沈清,胡德文,时春.神经网络应用技术.长沙:国防科技大学出版社.1993,12
[2]胡伍生.神经网络理论及其工程应用.北京:测绘出版社,2006,1
[3] Rafael C. Gonzalez,Richard E. Woods(著),阮秋琦,阮宇智(译).《数字图像处理》(第二版),北京:电子工业出版社,2003,3
[4]王向阳.关于图像压缩编码算法研究的综述.烟台师范学院学报.2001,17(4):288-295
[5]白月彬,卢华斌,韩庆绵等.图像压缩技术及其进展.微机发展.1996(4):24-26
[6] Yang Guowei,Li Zhengxi,Tu Xuyan.Lossless Data Compression Methods Based on Neural Network.Proceedings of ICCT2003:1899-1902
[7] S Costa,S Fiori.Image compression using principal component neural networks.Image and Vision Computing,2001(19):649-668
[8] M Egmont-Petersen,D de Ridder,H Handels.Image processing with neural networks-a review.Pattern Recognition,2002(35):2279-2301
[9] MARTIN T.HAGAN,HOWARD B.DEMUTH,MARK H.BEALE(著),戴葵(译).《神经网络设计》,北京:机械工业出版社,2002,9
[10]候媛彬,杜京义,汪梅.《神经网络》,西安:西安电子科技大学出版社.2007,08
[11]巫影,陈定方,唐小兵等.神经网络综述.科技进步与对策。2002(6):133-134
[12]冯春丽.基于改进型网络BP网络图像压缩方法的研究.辽宁工学院.硕士学位论文.2007年3月
[13]江芳泽,李昕.一种用于基于图像压缩的神经网络结构的研究.电子技术应用.1995.(7):8-10
[14]黄忠保.神经网络在图像压缩编码中的应用.湖北师范学院学报.1997.17(6):6-8
[15] Andre B. Soares, Altamiro A. Susin, Leticia V. Guimaraes. AutomaticGeneration of Neural Networks for Image Processing.2006 IEEE:3201-3204
[16]李丽芬,赵怀宇,刘书刚.神经网络在图像压缩中的应用研究,华北电力学报.2002,4.29(2):91-93
[17] Eduard Sackinger, Hans-Peter Graf. A Board System for High-Speed Image Analysis and Neural Networks. IEEE Trans. (on) NEURAL NETWORKS. 1996,1.1(1):214-221
[18] Scott Su, Alvin Lin, Jui-Cheng Yen. Design and Realization of A New Chaotic Neural Encryption Decryption Network. 2000 IEEE:335-338
[19] Marco Krips, Thomas Lammert, Anton Kummert. FPGA Implementation of a Neural Network for a Real-Time Hand Tracking System Proceedings of the First IEEE International Workshop on Electronic Design. Test and Applications (DELTA’02).2002 IEEE:169-172
[20]黎洪松,全子一.一种基于自组织神经网络的图像压缩编码算法.1996,1.24(1):6-11
[21]王虹,时文.基于神经网络的主分量分析及其在图像压缩中的应用研究.武汉理工大学学报(交通科学与工程版).2005,6.29(3):425-427
[22]许锋,卢建刚,孙优贤.神经网络在图像处理中的应用.信息与控制.2003,8.32(4):344-351
[23]刘春阳,粱德群,宋焕生等.神经网络在图像压缩技术中的应用.工程数学学报.1997,9.14(3):67-78
[24]戴彦群,卢玉蓉,王茂芝.用改进的SOFM算法实现快速矢量量化.四川师范大学学报,2003(26):69-71
[25]朱翔,吴贻鼎.基于自组织特征映射神经网络的图像压缩.计算机工程.2003,11.29(20):121-123
[26]张敏.基于改进BP网络的图像压缩.辽宁工学院学报.2007,8.27(4):258-262
[27]郑建华.图象数据压缩的BP神经网络方法研究.计算机仿真.2001,3.18(2):33-36
[28]周忠海,泮利,张奚宁等. BP神经网络及其在图像压缩中的应用.2006,6.4(6):139-140
[29]姚瑞波,孙国雄,汤崇熙.多层神经网络BP算法的改进.东南大学学报.1996,6.26(4):127-130
[30] J.Jiang.Image compression with neural networks--Asurvey. Signal Processing.Image Communication.1999:14.737~760.
[31] Hamdy S.Soliman.Mohammed Omari.A neural networks approach to image data compression.Applied Soft Computing.2006.6:258-271.
[32] Robert Cierniak, Leszek Rutkowski.On image compression by competitive neuralnetworks and optimal linear predictors.Signal Processing:Image Communication. 2000(15):559-565
[33] Ligang Ke, Michael W Marcellin. Near lossless image compression: Minimum-entropy, Constrained-error DPCM.IEEE Trans.(on) IMAGEPROCESSING.1998.7(2):1057-7149
[34] Koen Denecher,Dimitri Van De Ville,Frederik Habilset al.Design of an improved lossless halftone image compression codec. Signal Processing : Image Commu- nication.2002,17: 277-292.
[35]曾湧,沈未明,廖明生.基于小波变换及神经网络的图像压缩编码.测绘信息与工程.1997.(4):22-25
[36]武斌,李象霖.在小波变换域内应用BP网络进行图象压缩的方法研究.中国图象图形学报.1999,1.4(A)(1):23-27
[37]赵健,谢红梅,俞卞章等.基于神经网络的小波变换矢量量化图像压缩.陕西师范大学学报.2002,3.30(1):48-51
[38]王炼,小波变换和混合神经网络在图像压缩中的应用研究.哈尔滨工程大学.硕士学位论文.2005,12.
[39]张锐菊,周诠.神经网络用于遥感图像压缩的一些研究结果.中国体视学与图像分析.2003,9.8(3):183-186
[40]黄雪梅,唐治德.基于多层前馈神经网络的图像压缩的仿真研究.计算机仿真.2005,8.22(8):118-121
[41]赵宏怡.DSP技术与应用实例.北京:电子工业出版社.2003,6
[42]刘艳萍.DSP技术原理及应用教程.北京:北京航空航天大学出版社.2005
[43]褚振勇,齐亮,田红心等.FPGA设计及应用(第二版).西安:西安电子科技大学出版社.2006.12
[44] Wakerly(著).林生等(译).数字设计:原理与实践(原书第四版).北京:机械工业出版社.2007.5
[45]张雄伟,陈亮,徐光辉.DSP芯片原理与开发应用(第三版).北京:电子工业出版社.2003
[46]苏涛,蔺丽华.DSP实用技术.西安:西安电子科技大学出版社.2005
[47]沃尔夫(Wolf, W.)(著),闫敬文(译).基于FPGA的系统设计.北京:机械工业出版社,2006,5
[48] Bob Zeidman(著),赵宏图(译).基于FPGA&CPLD的数字IC设计方法.北京:北京航空航天大学出版社.2004,4
[49]田华,冯勤群,胡喜飞.基于DSP和FPGA的高速图像压缩系统设计.电子工程师.2005,8.31(8):51-52
[50] Philip P. Dang and Paul M. Chau. Hardware/Software Implementation 3-Way Algorithm for Image Encryption, In Security and Watermarking of Multimedia Contents II.Proceedings of SPIE
[51] Vladimír Havel, Karel Vek. Feasibility of Image Compression in FPGA based Neural Networks. Department of Computer Science. 2007 IEEE
[52] Wang Q, Yi B, Xie Y, et al. The hardware structure design of perceptron with FPGA implementation. Proceedings of IEEE International Conference on Systems, Man and Cybernetics. Washington D.C., 2003: 762
[53]张天序,邹胜,曾永慧.基于FPGA的图像无损压缩算法的实现,系统工程与电子技术.2004,10.26(10):1340-1343
[54]林三虎,李秋菊,赵亦工等.微型高速图像压缩系统.遥测遥控.2002,9.23(5):19-24
[55] Noriyuki Aibe, Moritoshi Yasunaga, Ikuo Yoshihara, etc. A probabilistic neural network hardware system using a learning-parameter parallel architecture.2002 IEEE:2270-2275
[56] Chih-hsied Kung, Michael J.Devaney, Chih-ming Kung, etc. The VLSI implementation of an artificial neural network scheme embedded in an automated inspection quality management system. IEEE Instrumentation and Measurement Technology Conference, Anchorage. 2002 IEEE:239-244
[57] Faiedh H, Gafsi Z, Torki K, et al. Digital hardware implementation of a neural networkused for classification. Proceedings of the 16th International Conference on Microelectronics. Tunis, 2004:551
[58]汪光森,伍行键,李誉.基于FPGA的神经网络的硬件实现.电子技术应用.1999(12):23-25
[59] Ming Z. Zhang, Ming-Jung Seow, Vijayan K. Asari. A Hardware Architecture for Color Image Enhancement Using a Machine Learning Approach with Adaptive Parameterization. 2006 International Joint Conference on Neural Networks. Vancouver, BC, Canada. 2006 IEEE:35-40
[60]张丽峰,杨光临,段晓辉等.双曲正切非线性函数和加均值量化算法对BP神经网络图像压缩处理的影响.工程图学学报.2006(1):110-115
[61]王雪光,郭艳兵,齐占庆.激活函数对BP网络性能的影响及其仿真研究.自动化技术与应用,2002, 21(4):15-17
[62] Christopher Cramer. Neural networks for image and video compression: a review. Euro- pean Journal of Operation Research,1998,108:266-282.
[63]王诚,吴继华等.Altera FPGA-CPLD设计(基础篇).北京:人民邮电出版社.2005.7
[64]王诚,吴继华等.Altera FPGA-CPLD设计(高级篇).北京:人民邮电出版社.2005.7
[65]刘宏宇,张尔扬.基于FFT-IFFT的高速卫星成形滤波器设计及其FPGA实现.无线通信技术.2006.(2):32-36
[66]张秀艳.基于FPGA的神经网络硬件实现中的关键问题研究.科技情报开发与经济.2005.15(5):273-275
[2]胡伍生.神经网络理论及其工程应用.北京:测绘出版社,2006,1
[3] Rafael C. Gonzalez,Richard E. Woods(著),阮秋琦,阮宇智(译).《数字图像处理》(第二版),北京:电子工业出版社,2003,3
[4]王向阳.关于图像压缩编码算法研究的综述.烟台师范学院学报.2001,17(4):288-295
[5]白月彬,卢华斌,韩庆绵等.图像压缩技术及其进展.微机发展.1996(4):24-26
[6] Yang Guowei,Li Zhengxi,Tu Xuyan.Lossless Data Compression Methods Based on Neural Network.Proceedings of ICCT2003:1899-1902
[7] S Costa,S Fiori.Image compression using principal component neural networks.Image and Vision Computing,2001(19):649-668
[8] M Egmont-Petersen,D de Ridder,H Handels.Image processing with neural networks-a review.Pattern Recognition,2002(35):2279-2301
[9] MARTIN T.HAGAN,HOWARD B.DEMUTH,MARK H.BEALE(著),戴葵(译).《神经网络设计》,北京:机械工业出版社,2002,9
[10]候媛彬,杜京义,汪梅.《神经网络》,西安:西安电子科技大学出版社.2007,08
[11]巫影,陈定方,唐小兵等.神经网络综述.科技进步与对策。2002(6):133-134
[12]冯春丽.基于改进型网络BP网络图像压缩方法的研究.辽宁工学院.硕士学位论文.2007年3月
[13]江芳泽,李昕.一种用于基于图像压缩的神经网络结构的研究.电子技术应用.1995.(7):8-10
[14]黄忠保.神经网络在图像压缩编码中的应用.湖北师范学院学报.1997.17(6):6-8
[15] Andre B. Soares, Altamiro A. Susin, Leticia V. Guimaraes. AutomaticGeneration of Neural Networks for Image Processing.2006 IEEE:3201-3204
[16]李丽芬,赵怀宇,刘书刚.神经网络在图像压缩中的应用研究,华北电力学报.2002,4.29(2):91-93
[17] Eduard Sackinger, Hans-Peter Graf. A Board System for High-Speed Image Analysis and Neural Networks. IEEE Trans. (on) NEURAL NETWORKS. 1996,1.1(1):214-221
[18] Scott Su, Alvin Lin, Jui-Cheng Yen. Design and Realization of A New Chaotic Neural Encryption Decryption Network. 2000 IEEE:335-338
[19] Marco Krips, Thomas Lammert, Anton Kummert. FPGA Implementation of a Neural Network for a Real-Time Hand Tracking System Proceedings of the First IEEE International Workshop on Electronic Design. Test and Applications (DELTA’02).2002 IEEE:169-172
[20]黎洪松,全子一.一种基于自组织神经网络的图像压缩编码算法.1996,1.24(1):6-11
[21]王虹,时文.基于神经网络的主分量分析及其在图像压缩中的应用研究.武汉理工大学学报(交通科学与工程版).2005,6.29(3):425-427
[22]许锋,卢建刚,孙优贤.神经网络在图像处理中的应用.信息与控制.2003,8.32(4):344-351
[23]刘春阳,粱德群,宋焕生等.神经网络在图像压缩技术中的应用.工程数学学报.1997,9.14(3):67-78
[24]戴彦群,卢玉蓉,王茂芝.用改进的SOFM算法实现快速矢量量化.四川师范大学学报,2003(26):69-71
[25]朱翔,吴贻鼎.基于自组织特征映射神经网络的图像压缩.计算机工程.2003,11.29(20):121-123
[26]张敏.基于改进BP网络的图像压缩.辽宁工学院学报.2007,8.27(4):258-262
[27]郑建华.图象数据压缩的BP神经网络方法研究.计算机仿真.2001,3.18(2):33-36
[28]周忠海,泮利,张奚宁等. BP神经网络及其在图像压缩中的应用.2006,6.4(6):139-140
[29]姚瑞波,孙国雄,汤崇熙.多层神经网络BP算法的改进.东南大学学报.1996,6.26(4):127-130
[30] J.Jiang.Image compression with neural networks--Asurvey. Signal Processing.Image Communication.1999:14.737~760.
[31] Hamdy S.Soliman.Mohammed Omari.A neural networks approach to image data compression.Applied Soft Computing.2006.6:258-271.
[32] Robert Cierniak, Leszek Rutkowski.On image compression by competitive neuralnetworks and optimal linear predictors.Signal Processing:Image Communication. 2000(15):559-565
[33] Ligang Ke, Michael W Marcellin. Near lossless image compression: Minimum-entropy, Constrained-error DPCM.IEEE Trans.(on) IMAGEPROCESSING.1998.7(2):1057-7149
[34] Koen Denecher,Dimitri Van De Ville,Frederik Habilset al.Design of an improved lossless halftone image compression codec. Signal Processing : Image Commu- nication.2002,17: 277-292.
[35]曾湧,沈未明,廖明生.基于小波变换及神经网络的图像压缩编码.测绘信息与工程.1997.(4):22-25
[36]武斌,李象霖.在小波变换域内应用BP网络进行图象压缩的方法研究.中国图象图形学报.1999,1.4(A)(1):23-27
[37]赵健,谢红梅,俞卞章等.基于神经网络的小波变换矢量量化图像压缩.陕西师范大学学报.2002,3.30(1):48-51
[38]王炼,小波变换和混合神经网络在图像压缩中的应用研究.哈尔滨工程大学.硕士学位论文.2005,12.
[39]张锐菊,周诠.神经网络用于遥感图像压缩的一些研究结果.中国体视学与图像分析.2003,9.8(3):183-186
[40]黄雪梅,唐治德.基于多层前馈神经网络的图像压缩的仿真研究.计算机仿真.2005,8.22(8):118-121
[41]赵宏怡.DSP技术与应用实例.北京:电子工业出版社.2003,6
[42]刘艳萍.DSP技术原理及应用教程.北京:北京航空航天大学出版社.2005
[43]褚振勇,齐亮,田红心等.FPGA设计及应用(第二版).西安:西安电子科技大学出版社.2006.12
[44] Wakerly(著).林生等(译).数字设计:原理与实践(原书第四版).北京:机械工业出版社.2007.5
[45]张雄伟,陈亮,徐光辉.DSP芯片原理与开发应用(第三版).北京:电子工业出版社.2003
[46]苏涛,蔺丽华.DSP实用技术.西安:西安电子科技大学出版社.2005
[47]沃尔夫(Wolf, W.)(著),闫敬文(译).基于FPGA的系统设计.北京:机械工业出版社,2006,5
[48] Bob Zeidman(著),赵宏图(译).基于FPGA&CPLD的数字IC设计方法.北京:北京航空航天大学出版社.2004,4
[49]田华,冯勤群,胡喜飞.基于DSP和FPGA的高速图像压缩系统设计.电子工程师.2005,8.31(8):51-52
[50] Philip P. Dang and Paul M. Chau. Hardware/Software Implementation 3-Way Algorithm for Image Encryption, In Security and Watermarking of Multimedia Contents II.Proceedings of SPIE
[51] Vladimír Havel, Karel Vek. Feasibility of Image Compression in FPGA based Neural Networks. Department of Computer Science. 2007 IEEE
[52] Wang Q, Yi B, Xie Y, et al. The hardware structure design of perceptron with FPGA implementation. Proceedings of IEEE International Conference on Systems, Man and Cybernetics. Washington D.C., 2003: 762
[53]张天序,邹胜,曾永慧.基于FPGA的图像无损压缩算法的实现,系统工程与电子技术.2004,10.26(10):1340-1343
[54]林三虎,李秋菊,赵亦工等.微型高速图像压缩系统.遥测遥控.2002,9.23(5):19-24
[55] Noriyuki Aibe, Moritoshi Yasunaga, Ikuo Yoshihara, etc. A probabilistic neural network hardware system using a learning-parameter parallel architecture.2002 IEEE:2270-2275
[56] Chih-hsied Kung, Michael J.Devaney, Chih-ming Kung, etc. The VLSI implementation of an artificial neural network scheme embedded in an automated inspection quality management system. IEEE Instrumentation and Measurement Technology Conference, Anchorage. 2002 IEEE:239-244
[57] Faiedh H, Gafsi Z, Torki K, et al. Digital hardware implementation of a neural networkused for classification. Proceedings of the 16th International Conference on Microelectronics. Tunis, 2004:551
[58]汪光森,伍行键,李誉.基于FPGA的神经网络的硬件实现.电子技术应用.1999(12):23-25
[59] Ming Z. Zhang, Ming-Jung Seow, Vijayan K. Asari. A Hardware Architecture for Color Image Enhancement Using a Machine Learning Approach with Adaptive Parameterization. 2006 International Joint Conference on Neural Networks. Vancouver, BC, Canada. 2006 IEEE:35-40
[60]张丽峰,杨光临,段晓辉等.双曲正切非线性函数和加均值量化算法对BP神经网络图像压缩处理的影响.工程图学学报.2006(1):110-115
[61]王雪光,郭艳兵,齐占庆.激活函数对BP网络性能的影响及其仿真研究.自动化技术与应用,2002, 21(4):15-17
[62] Christopher Cramer. Neural networks for image and video compression: a review. Euro- pean Journal of Operation Research,1998,108:266-282.
[63]王诚,吴继华等.Altera FPGA-CPLD设计(基础篇).北京:人民邮电出版社.2005.7
[64]王诚,吴继华等.Altera FPGA-CPLD设计(高级篇).北京:人民邮电出版社.2005.7
[65]刘宏宇,张尔扬.基于FFT-IFFT的高速卫星成形滤波器设计及其FPGA实现.无线通信技术.2006.(2):32-36
[66]张秀艳.基于FPGA的神经网络硬件实现中的关键问题研究.科技情报开发与经济.2005.15(5):273-275