敦煌壁画颜色还原校正方法的研究
|
摘要
敦煌壁画颜色在不同设备(媒质)上复制再现时的颜色校正还原问题,一直是人们关注的热点问题,是文物保护的重要指标之一。敦煌壁画颜色“色彩传递,一致再现”也是敦煌学研究的重要组成部分。
通过分析数码相机到显示器,显示器到彩色打印机的颜色校正还原方法,本文建立了一个全色域范围下的实用可操作的颜色校正还原系统,使壁画图像由数码相机摄取,到计算机处理,再经彩色打印的全系统传输后,彩印出的壁画颜色能够“准确真实”地表现原壁画的颜色。
研究了色域匹配的现有方法,采用了人工神经网络的匹配方法。通过对神经网络的优化设计和学习训练,使该神经网络的权值和阈值得到了充分的信息储存,实现了彩色打印机的L~*a~*b~*色域空间向显示器的RGB色域空间的色域匹配,避免了其它方法的局限性,得到了较好的色域匹配预测值。
由于人工神经网络隐层神经元节点数的确定尚无理论规律可寻,本文提出了应用二次通用旋转组合设计与遗传算法结合,优化得到人工神经网络隐层神经元节点数的方法。本方法也为多隐层人工神经网络隐层神经元节点数的确定奠定了理论基础。
建立了修正三基色值的双隐层人工神经网络,并将修正三基色值的人工神经网络与VC程序嵌套,只需对图像像素三基色值进行修正,便可得到最终的敦煌壁画颜色的校正还原,实现了校正复杂颜色失真过程的简单化。
使用Macbeth ColorChecker Chart对该颜色校正系统进行色差检验,平均色差由校正前的17.1NBS,最大色差37.0NBS,最小色差4.3NBS,降到校正后的平均色差5.3NBS,最大色差12.4NBS,最小色差1.7NBS。取得了较好的客观颜色校正效果,主观评定方面也得到了业内专家的肯定。
Dunhuang mural color correction is a hot problem all along when it is reproduced or reappeared on different equipment (medium), it is one of the important indexes on cultural relic protection, achieving the same color reappearance along with the Dunhuang mural transferred, is also an important part of Dunhuang study.By analyzing the color correction method from digital camera to CRT, and from CRT to color printer, the color correction system is established, which can be operated practically under a big color gamut. After transferred through the whole system equipment, which included taking picture with digital camera, computer processing and color copying, the final picture we got from color printer can show the original mural color accurately.Based on the study of color gamut matching method in existence, the matching method of artificial neural network is adopted. With the optimization design and the training of the artificial neural network, ample information is stored in weight and threshold value of the artificial neural network. The color gamut matching is realized from the L*a b color space of the color printer to RGB color space of the CRT, this method can avoid the deficiency of other, and get better forecasting value of color gamut matching.Because of no theory or principle to decide the number of hide-layer neural cell of the artificial neural network, the method combined second general revolving combination design with genetic algorithm is put forward, which can optimize the hide-layer neural cell number of artificial neural network. This method provided theory foundation for the structure establishment of hide-layer neural cell of artificial neural network also.The artificial neural network including two hide-layers is established, which can correct the tristimulus values, the weight and threshold value of this artificial neural network is gained, and the artificial neural network is nested in the computer program compiled by VC language. The color correction of the last Dunhuang mural picture can be finished after the tristimulus values of image pixel are corrected, and the process simplified correcting the complex color distortion has been realized.Using Macbeth ColorChecker Chart, the color difference of this color correction system is tested. Before correction, average color difference is 17.1 NBS, the maximum color difference is 37.0 NBS, and the minimum color difference is 4.3NBS;
while after correction, the average color difference is reduced to 5.3 NBS, the maximum color difference is 12.4 NBS, and the minimum color difference is 1.7 NBS. Ideal objective effect of color correction has been gotten and expert in this domain has praised the work.
通过分析数码相机到显示器,显示器到彩色打印机的颜色校正还原方法,本文建立了一个全色域范围下的实用可操作的颜色校正还原系统,使壁画图像由数码相机摄取,到计算机处理,再经彩色打印的全系统传输后,彩印出的壁画颜色能够“准确真实”地表现原壁画的颜色。
研究了色域匹配的现有方法,采用了人工神经网络的匹配方法。通过对神经网络的优化设计和学习训练,使该神经网络的权值和阈值得到了充分的信息储存,实现了彩色打印机的L~*a~*b~*色域空间向显示器的RGB色域空间的色域匹配,避免了其它方法的局限性,得到了较好的色域匹配预测值。
由于人工神经网络隐层神经元节点数的确定尚无理论规律可寻,本文提出了应用二次通用旋转组合设计与遗传算法结合,优化得到人工神经网络隐层神经元节点数的方法。本方法也为多隐层人工神经网络隐层神经元节点数的确定奠定了理论基础。
建立了修正三基色值的双隐层人工神经网络,并将修正三基色值的人工神经网络与VC程序嵌套,只需对图像像素三基色值进行修正,便可得到最终的敦煌壁画颜色的校正还原,实现了校正复杂颜色失真过程的简单化。
使用Macbeth ColorChecker Chart对该颜色校正系统进行色差检验,平均色差由校正前的17.1NBS,最大色差37.0NBS,最小色差4.3NBS,降到校正后的平均色差5.3NBS,最大色差12.4NBS,最小色差1.7NBS。取得了较好的客观颜色校正效果,主观评定方面也得到了业内专家的肯定。
Dunhuang mural color correction is a hot problem all along when it is reproduced or reappeared on different equipment (medium), it is one of the important indexes on cultural relic protection, achieving the same color reappearance along with the Dunhuang mural transferred, is also an important part of Dunhuang study.By analyzing the color correction method from digital camera to CRT, and from CRT to color printer, the color correction system is established, which can be operated practically under a big color gamut. After transferred through the whole system equipment, which included taking picture with digital camera, computer processing and color copying, the final picture we got from color printer can show the original mural color accurately.Based on the study of color gamut matching method in existence, the matching method of artificial neural network is adopted. With the optimization design and the training of the artificial neural network, ample information is stored in weight and threshold value of the artificial neural network. The color gamut matching is realized from the L*a b color space of the color printer to RGB color space of the CRT, this method can avoid the deficiency of other, and get better forecasting value of color gamut matching.Because of no theory or principle to decide the number of hide-layer neural cell of the artificial neural network, the method combined second general revolving combination design with genetic algorithm is put forward, which can optimize the hide-layer neural cell number of artificial neural network. This method provided theory foundation for the structure establishment of hide-layer neural cell of artificial neural network also.The artificial neural network including two hide-layers is established, which can correct the tristimulus values, the weight and threshold value of this artificial neural network is gained, and the artificial neural network is nested in the computer program compiled by VC language. The color correction of the last Dunhuang mural picture can be finished after the tristimulus values of image pixel are corrected, and the process simplified correcting the complex color distortion has been realized.Using Macbeth ColorChecker Chart, the color difference of this color correction system is tested. Before correction, average color difference is 17.1 NBS, the maximum color difference is 37.0 NBS, and the minimum color difference is 4.3NBS;
while after correction, the average color difference is reduced to 5.3 NBS, the maximum color difference is 12.4 NBS, and the minimum color difference is 1.7 NBS. Ideal objective effect of color correction has been gotten and expert in this domain has praised the work.
引文
[1] 刘钢,李实.敦煌壁画计算机存储与再现系统的平台建设.敦煌研究,2000,1: 100-102.
[2] 刘钢,李实.敦煌壁画计算机存储与再现系统的目标与实现.敦煌研究,2000,1:95-99.
[3] 周丰昆,陈淑芳,王喜昌,刘钢,李实.敦煌壁画计算机存储与管理中的颜色还原校正.敦煌研究,1996,2:168-171.
[4] Stone. Special report about color management. 2003, Available at: http//www.color.org/tc8-03.
[5]杜桂华,李伟,卢瑞琪,王四诊,任云.色域匹配纵览.印刷世界,2004,1:8-12.
[6] Fritz Ebner, Mard D. Fairchild. Gamut mapping from below: Finding minimum perceptual distances for colors outside the gamut volume, color research and application, 402-413.
[7] 黄庆梅,赵达尊.彩色复制中的色域映射.照明工程学报,2002,13(1),19—26.
[8] 苏晓红,王亚东,郭茂祖.基于样本空间学习算法的彩色匹配方法研究.自动化学报,2001,27(2):186—193.
[9] Naoya Katoh, Masahiko Ito. Appling Non-linear Compression to the Three-dimensional Gamut Mappin. Journal of imaging and technology, 2000, 44 (4): 328—333.
[10] K. E. Spaulding, R. N. Ellson, J. R. Sullivan. Ultra Color, A new gamut mapping strategy. Proc. SPIE, 1995, 2414: 61-68.
[11] H. Motomura. Categorical Color Mapping for Gamut Mapping-Using Block Average Image. SPIE, 1999, 3648: 108-119.
[12] L. W. Macdonald. Gamut Mapping in perceptual Color Space. Proceedings of 1st IS/SID Color imaging Conference. IS & T, Sping field, VA, 1993, 193-196.
[13] 常城,齐春.彩色记录与重现系统.中国图像图形学报,2001,6(3):205～ 213.
[14] Cheol-Hee, Eung-Joo Lee, Sunk-Chul Ann, Yeong-Ho Ha. Color space conversion via gamut-based color samples of printer. 2001, 45(5): 427-435.
[15] (美)ROY S.Berns.颜色技术原理.化学工业出版社.
[16] 崔元日.印刷图像学.解放军出版社,256～269.
[17] G. Lrogers. Neugebauer revisited: random dots in halfone screening. Color research and application, 1998, 23:104～113.
[18] A. C. Yule, W. J. Nielsn. The penetration of light into paper and its effects on halftone reproduction. Pro.Tech Asson Graphics Arts, 1951 (4): 65～75.
[19] F. R. Clapper, J. A. C. Yule. The effect of multiple internal reflections on the densities of half-tone prints on paper. J. Optical Soc. Amr, 1953(43): 600～603.
[20] R Kubelka. New conteibutions to optics of intensely light-scattering materials (Part I). J. Opt. Soc. Am, 1948(38): 448～457.
[21] Hery R. Kang. Printers related color printers processing techniches. SPIE, 2413: 410-419.
[22] K. Knanmori. Fast color processor with programmable interpolation by small memory. J. Electronic Imaging, 1992(36): 73-78.
[23] K. D. Genntten. RGB to CMYK conversion using 3D barycentric interpolation Proc. SPIE, 1993, 1909:117-123.
[24] J. M. kasson, S. L. Nin, W. Plouffe, J. L. Haffner. Performing color space conversions with three-dimensional linear interpolation. J. Electrnoc Imaging, 1995(4): 226-250.
[25] Po-Chieh Hung. Colorimetric Calibration for Scanners and Media [J]. SPIE, Vol. 1448: 164～174.
[26] M. Xia, E. Esaber, A. M. Tekalp. End-to-end color printer calibration by total least squares regression [J], IEEE Transactions on Image imaging processing. 1999, 8: 700-716.
[27] 李忠范,高文森.数理统计,吉林大学出版社.
[28] Henry R. Kang. Color scanner calibration. Journal of imaging science and technology, 1992, 36(2): 162-170.
[29] H. R. Kang. Coloe scanner calibration of reflected samples. SPIE, 1992, 1670: I68～482.
[30] S. Tominaga. Color control of printers by neural network [J]. J. Electronic imaging. 1998(7): 664～671.
[31] S. Tominaga. Color notation conversion by neural networks [J]. Color research and application, 1993, 18: 253～259.
[32] GUO M Z, WANG Y H, SU X H, WANG X Q. Research of color matching method on BP Network [J]. J. computer, Vol. 23: 819～823.
[33] ZHOU SH Q, ZHAO D Z. BP network based on color control in color printers [J]. Optics technique, 2000, 26(1), 49～51.
[34] Liao Ningfang, Gao Zhiyun. A comparative study of a CRT colorimetric prediction model by neural networks and the models by conventional method. Color research and application. 1999, 24(1): 45-50.
[35] 卜智翔,李爱农.基于BP神经网络预测药芯焊条耐磨性,武汉理工大学,1—3.
[36] 赵忠旭,沈兰荪,卫爱民等.基于人工神经网络的彩色校正方法研究.中国图像图形学报,5(9):785—789.
[37] Po-Chieh Hung. Colorimetric Calibration for Scanners and Media [J]. SPIE, Vol. 1448: 164～174.
[38] M. Xia, E. Esaber, A. M. Tekalp. End-to-end color printer calibration by total least squares regression [J]. IEEE Transactions on Image Processing, 1999, 8: 700～716.
[39] 闻新,周露,王丹力.神经网络应用设计.科学出版社.
[40] 荆其诚.色度学.科学出版社,112～114.
[41] 杨发权,李武纲,李玉祥.不同色度空间的颜色分离方法.2000,16(2):72～76.
[42] 刘文耀.光电图像处理.电子工业出版社,20～34.
[43] 陈鸿兴,陈君彦.基础色彩再现工程.全华科技,第一版,2003,90-96.
[44] 杨发权,李武纲,李玉祥.不同色度空间的颜色分离方法.2000,16(2):72～76.
[45] 刘文耀.光电图像处理.电子工业出版社,20～34.
[46] Roy S.Berns.颜色技术原理.化学工业出版社,第一版,2002,178.
[47] 蒋绍全,石俊生.数字彩色图像颜色管理.云南师范大学学报,2002,22(5):28—32.
[48] 徐丹,荣耀生,石教英.基于ICC标准的色彩管理研究.软件学报,1998,9(10):740—747.
[49] Lindsay W MacDonald. Developments in color management systems. Displays, 1996, Vol. 16, No. 4, 203-211.
[50] Peter A Rhodes, M Ronnier Luo. A system for WYSIWYG color communication. Displys, 1996, Vol. 16, No. 4,213-221.
[51] Microsoft windows. Color management and Microsoft windows operating systems, Jan. 1997, Available at: http://www.Microsoft.com/hwdev/devdes/icm.html.
[52] Michael H, Todd N. Color management: Current practice and the Adoption of a New Standard. Available at: http://www.color.org/overview.html.
[53] Improved Color for the Word Wide Web: A Case Study in Color Mangement for Distributed Digital Media. Available at: http://www.color.org/zwwwcolor.html.
[54] Fairchild M D, Berns R S. Image color appearance specification through extension of CIELAB. Color Research and Application, 1993, Vol.18, No.3, 178-190.
[55] Viggiano J A S, Wang C J. A comparison of algorithms for mapping color between media of differing luminance ranges. Proceedings of the Technical Association for the Graphic Arts, 1992, Vol. 2, 959-974.
[56] B. J. Lindbloom. Accurate color reproduction for computer graphics applications. Computer Graphics, 1989, Vol. 23, No. 3, 117-126.
[57] Johnson A. J. Techniques for reproducing image in different media: advantages and disadvantages of current methods. Proc. TAGA/ISCC Conf., 1992, Vol. 2, 739-755.
[58] 胡涛,张二虎,王歆平.计算机CRT设备特征描述文件的建立.计算机工 程,2002,28(10).
[59] ICC Profile Format specification Version 3.4, International Color Consortium. Available at: http://color.org.
[60] 徐丹,蒙耀生,石教英.基于ICC标准的色彩管理研究.软件学报,1998,Vol.9,No.10,740-747.
[61] 吴丽.数码相机的色彩管理.数码影像.2002(6):57-59.
[62] 张键.彩色屏幕的多灰度硬拷贝技术.计算机应用研究,1994(6):64-67.
[63] 何志强.图像抖动技术和原理及实现.计算机系统应用,1999(7):43～46.
[64] 李明,王燕.基于填充曲线的的抖动模式研究.信息技术,2001(4):29.
[65] 盛龙.在16色下显示256色及全彩色.PC应用,2000(3):46～49.
[66] Rumelhart D. E., McClelland J. L., eds. Parallel Distributed Processing: Exploration in the Microstructure of Cognition. 1986, vol. 1, Cambridge, MA: MIT Press.
[67] Richard P Lippmann. An Introduction to Computing with Neural Nets. IEEE ASSP Magazine, 1987: 4～22.
[68] SChen, S A Billings, P M Grant. Non-linear System Identification Using Neural Networks. Int. J. Control, 1990, 51(6): 1191～1214.
[69] Simon Haykin. Neural Networks: a Comprehensive Foundation [sencond edition].
[70] Rumelhart D. E., Hinton G. E., Williams R. J. Learning representations of back-propagation errors. Nature (London), 1986a, Vol. 323: 533～536.
[71] Rumelhart D. E., Hinton G. E., Williams R. J. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McCeland, eds., 1986b, vol 1, Chapter 8, Cambridge, MA: MIT Press.
[72] Rumelhart D. E., Zipser D. Feature discovery by competitive learning. Cognitive Science, 1985, 9: 75～112.
[73] 王文成.神经网络及其在汽车工程中的应用.北京理工大学出版社,1998.
[74] 袁曾任.人工神经元网络及其应用.清华大学出版社,2000.
[75] 杨秀坤.农产品品质检测中的人工智能方法研究.吉林工业大学博士学位 论文,1997.
[76] 楼顺天,施阳.基于MATLAB的系统分析与设计一神经网络.西安电子科技大学出版社,1999.
[77] 任露泉.试验优化技术.北京:机械工业出版社.
[78] David E. Goldberg. Genetic algorithms in Search, Optimization and Machine Learning. Addison-Wesley Pub. Co, 1989.
[79] Davis Lawrence. Handbook of Genetic Algorithms. Van Nostrand Reinhold, 1991.
[80] Goldberg, Santanic. Via GA, Pro. of 9th Conference on Electronic Computation. Eng. Opt, 1987 (9): 471～482.
[81] Hajala Lin CY. GA Strategies in multic-riterion optimal design. AIAA, 1991, 29(5): 1040～1046.
[82] Rajew. S, Krishanamoovthy. D. S. Discrete optimization of structures using Genetic Algorithms. Journal of Structural Engineering, 1992, 118(5):1233～ 1250.
[83] Holland J H. Adaptation in nature and artificial system. Ann Arbor: University of Michigan Press, 1975:11～14.
[84] Freeman L. M., et al. Turning fuzzy logic controller using genetic algorithms in aerospace applications. In Proceeing of the AAAIC'90 Conference, Dayton, Oct., 1990: 351～358.
[85] Glover F., et al. Genetic algorithms and tabu search: hybrids for optimization. Computer and Operation Research (UK), 1995, 122(1):111～134.
[86] McAulay A. D., Oh J. C. Improving learning of genetic rule-based classifier systems. IEEE Trans. On System, Man, and Cybernetics, 1994, 24(1):152～159.
[87] Matwin S., et al. Genetic algorithms approach to a negotiation support system. IEEE Trans. On Systems, Man and Cybernetics, 1991, 21 (1): 102～114.
[88] Qi, X. F., Palmieri E Adaptive mutation in the genetic algorithm. In Proceedings of the Second Annual Conference on Evolutionary. Programming. Fogel D. B., Atmar W., La Jolla (eds.), CA: Evolutionary Programming Society, 1993: 192～196.
[89] Chandrasekharam R., et al. Genetic algorithm for embedding a complete graph in a hypercube with a VLSI application. Micro-processing and Micro-programming, 1994, 40: 537～552.
[90] 李灏荃.遗传算法及神经网络在数据融合中的应用.西安电子科技大学硕士学位论文,1998.
[91] 李敏强等.遗传算法的基本理论与应用,北京:科学出版社.
[92] Whitley, L. D. (ed.) Foundations of genetic algorithms 2. San Mateo, CA: Morgan Kaufmann, 1993.
[93] Whitley L. D., Vose M. D. (eds.) Foundations of genetic algorithms 3. San Mateo, CA: Morgan Kaufmann, 1995.
[94] Melanie Mitchell. An introduction to genetic algorithms. Cambridge, MA: The MIT Press, 1996.
[95] Michalewicz Z. Genetic algorithm+Data structures=Evolution programs. AI Series. New York: Springer-Verlag, 1994.
[96] Holland J H. Genetic algorithm. Scientific American, July 1992, 253: 66.
[97] Jing K D. Learning with genetic algorithms: An overview. Machine Learning, 1988, 3: 121.
[98] Davis L. Handbook of genetic algorithms. 1st ed. Van Nostrand Reinhold, New York, 1991: 91～98.
[99] Goldberg D E. Genetic algorithm in search, optimization and machine learning. MA: Addison-Wesley Publishing Company, 1989
[100] De Jong, K. A. An analysis of the behavior of a class of genetic adaptive systems (Ph. D Dissertation). University of Michigan, No. 76～9381, 1975.
[101] Grefenstette, J. J. Optimization of control parameters for genetic algorithms. IEEE Transaction on Systems, Man, and Cybernetics, 1986, 16(1): 122～128.
[102] Schaffer, J. D. A study of control parameters affecting on-line performance of genetic algorithms for function optimization. In Proceedings of the Third International Conference on Genetic Algorithms (ICGA 3), Schaffer, J. D. (ed.), San Mateo, CA: Morgan Kaufmann Publishers, 1989:51～60.
[103] 王雪晶.彩色遥感图像的补偿与修正.中国科学院研究生院博士学位研究生学位论文,2002.
[104] 付建华.彩色打印机色彩空间转换方法研究.中国科学院研究生院硕士学位研究生学位论文,2004.
[2] 刘钢,李实.敦煌壁画计算机存储与再现系统的目标与实现.敦煌研究,2000,1:95-99.
[3] 周丰昆,陈淑芳,王喜昌,刘钢,李实.敦煌壁画计算机存储与管理中的颜色还原校正.敦煌研究,1996,2:168-171.
[4] Stone. Special report about color management. 2003, Available at: http//www.color.org/tc8-03.
[5]杜桂华,李伟,卢瑞琪,王四诊,任云.色域匹配纵览.印刷世界,2004,1:8-12.
[6] Fritz Ebner, Mard D. Fairchild. Gamut mapping from below: Finding minimum perceptual distances for colors outside the gamut volume, color research and application, 402-413.
[7] 黄庆梅,赵达尊.彩色复制中的色域映射.照明工程学报,2002,13(1),19—26.
[8] 苏晓红,王亚东,郭茂祖.基于样本空间学习算法的彩色匹配方法研究.自动化学报,2001,27(2):186—193.
[9] Naoya Katoh, Masahiko Ito. Appling Non-linear Compression to the Three-dimensional Gamut Mappin. Journal of imaging and technology, 2000, 44 (4): 328—333.
[10] K. E. Spaulding, R. N. Ellson, J. R. Sullivan. Ultra Color, A new gamut mapping strategy. Proc. SPIE, 1995, 2414: 61-68.
[11] H. Motomura. Categorical Color Mapping for Gamut Mapping-Using Block Average Image. SPIE, 1999, 3648: 108-119.
[12] L. W. Macdonald. Gamut Mapping in perceptual Color Space. Proceedings of 1st IS/SID Color imaging Conference. IS & T, Sping field, VA, 1993, 193-196.
[13] 常城,齐春.彩色记录与重现系统.中国图像图形学报,2001,6(3):205～ 213.
[14] Cheol-Hee, Eung-Joo Lee, Sunk-Chul Ann, Yeong-Ho Ha. Color space conversion via gamut-based color samples of printer. 2001, 45(5): 427-435.
[15] (美)ROY S.Berns.颜色技术原理.化学工业出版社.
[16] 崔元日.印刷图像学.解放军出版社,256～269.
[17] G. Lrogers. Neugebauer revisited: random dots in halfone screening. Color research and application, 1998, 23:104～113.
[18] A. C. Yule, W. J. Nielsn. The penetration of light into paper and its effects on halftone reproduction. Pro.Tech Asson Graphics Arts, 1951 (4): 65～75.
[19] F. R. Clapper, J. A. C. Yule. The effect of multiple internal reflections on the densities of half-tone prints on paper. J. Optical Soc. Amr, 1953(43): 600～603.
[20] R Kubelka. New conteibutions to optics of intensely light-scattering materials (Part I). J. Opt. Soc. Am, 1948(38): 448～457.
[21] Hery R. Kang. Printers related color printers processing techniches. SPIE, 2413: 410-419.
[22] K. Knanmori. Fast color processor with programmable interpolation by small memory. J. Electronic Imaging, 1992(36): 73-78.
[23] K. D. Genntten. RGB to CMYK conversion using 3D barycentric interpolation Proc. SPIE, 1993, 1909:117-123.
[24] J. M. kasson, S. L. Nin, W. Plouffe, J. L. Haffner. Performing color space conversions with three-dimensional linear interpolation. J. Electrnoc Imaging, 1995(4): 226-250.
[25] Po-Chieh Hung. Colorimetric Calibration for Scanners and Media [J]. SPIE, Vol. 1448: 164～174.
[26] M. Xia, E. Esaber, A. M. Tekalp. End-to-end color printer calibration by total least squares regression [J], IEEE Transactions on Image imaging processing. 1999, 8: 700-716.
[27] 李忠范,高文森.数理统计,吉林大学出版社.
[28] Henry R. Kang. Color scanner calibration. Journal of imaging science and technology, 1992, 36(2): 162-170.
[29] H. R. Kang. Coloe scanner calibration of reflected samples. SPIE, 1992, 1670: I68～482.
[30] S. Tominaga. Color control of printers by neural network [J]. J. Electronic imaging. 1998(7): 664～671.
[31] S. Tominaga. Color notation conversion by neural networks [J]. Color research and application, 1993, 18: 253～259.
[32] GUO M Z, WANG Y H, SU X H, WANG X Q. Research of color matching method on BP Network [J]. J. computer, Vol. 23: 819～823.
[33] ZHOU SH Q, ZHAO D Z. BP network based on color control in color printers [J]. Optics technique, 2000, 26(1), 49～51.
[34] Liao Ningfang, Gao Zhiyun. A comparative study of a CRT colorimetric prediction model by neural networks and the models by conventional method. Color research and application. 1999, 24(1): 45-50.
[35] 卜智翔,李爱农.基于BP神经网络预测药芯焊条耐磨性,武汉理工大学,1—3.
[36] 赵忠旭,沈兰荪,卫爱民等.基于人工神经网络的彩色校正方法研究.中国图像图形学报,5(9):785—789.
[37] Po-Chieh Hung. Colorimetric Calibration for Scanners and Media [J]. SPIE, Vol. 1448: 164～174.
[38] M. Xia, E. Esaber, A. M. Tekalp. End-to-end color printer calibration by total least squares regression [J]. IEEE Transactions on Image Processing, 1999, 8: 700～716.
[39] 闻新,周露,王丹力.神经网络应用设计.科学出版社.
[40] 荆其诚.色度学.科学出版社,112～114.
[41] 杨发权,李武纲,李玉祥.不同色度空间的颜色分离方法.2000,16(2):72～76.
[42] 刘文耀.光电图像处理.电子工业出版社,20～34.
[43] 陈鸿兴,陈君彦.基础色彩再现工程.全华科技,第一版,2003,90-96.
[44] 杨发权,李武纲,李玉祥.不同色度空间的颜色分离方法.2000,16(2):72～76.
[45] 刘文耀.光电图像处理.电子工业出版社,20～34.
[46] Roy S.Berns.颜色技术原理.化学工业出版社,第一版,2002,178.
[47] 蒋绍全,石俊生.数字彩色图像颜色管理.云南师范大学学报,2002,22(5):28—32.
[48] 徐丹,荣耀生,石教英.基于ICC标准的色彩管理研究.软件学报,1998,9(10):740—747.
[49] Lindsay W MacDonald. Developments in color management systems. Displays, 1996, Vol. 16, No. 4, 203-211.
[50] Peter A Rhodes, M Ronnier Luo. A system for WYSIWYG color communication. Displys, 1996, Vol. 16, No. 4,213-221.
[51] Microsoft windows. Color management and Microsoft windows operating systems, Jan. 1997, Available at: http://www.Microsoft.com/hwdev/devdes/icm.html.
[52] Michael H, Todd N. Color management: Current practice and the Adoption of a New Standard. Available at: http://www.color.org/overview.html.
[53] Improved Color for the Word Wide Web: A Case Study in Color Mangement for Distributed Digital Media. Available at: http://www.color.org/zwwwcolor.html.
[54] Fairchild M D, Berns R S. Image color appearance specification through extension of CIELAB. Color Research and Application, 1993, Vol.18, No.3, 178-190.
[55] Viggiano J A S, Wang C J. A comparison of algorithms for mapping color between media of differing luminance ranges. Proceedings of the Technical Association for the Graphic Arts, 1992, Vol. 2, 959-974.
[56] B. J. Lindbloom. Accurate color reproduction for computer graphics applications. Computer Graphics, 1989, Vol. 23, No. 3, 117-126.
[57] Johnson A. J. Techniques for reproducing image in different media: advantages and disadvantages of current methods. Proc. TAGA/ISCC Conf., 1992, Vol. 2, 739-755.
[58] 胡涛,张二虎,王歆平.计算机CRT设备特征描述文件的建立.计算机工 程,2002,28(10).
[59] ICC Profile Format specification Version 3.4, International Color Consortium. Available at: http://color.org.
[60] 徐丹,蒙耀生,石教英.基于ICC标准的色彩管理研究.软件学报,1998,Vol.9,No.10,740-747.
[61] 吴丽.数码相机的色彩管理.数码影像.2002(6):57-59.
[62] 张键.彩色屏幕的多灰度硬拷贝技术.计算机应用研究,1994(6):64-67.
[63] 何志强.图像抖动技术和原理及实现.计算机系统应用,1999(7):43～46.
[64] 李明,王燕.基于填充曲线的的抖动模式研究.信息技术,2001(4):29.
[65] 盛龙.在16色下显示256色及全彩色.PC应用,2000(3):46～49.
[66] Rumelhart D. E., McClelland J. L., eds. Parallel Distributed Processing: Exploration in the Microstructure of Cognition. 1986, vol. 1, Cambridge, MA: MIT Press.
[67] Richard P Lippmann. An Introduction to Computing with Neural Nets. IEEE ASSP Magazine, 1987: 4～22.
[68] SChen, S A Billings, P M Grant. Non-linear System Identification Using Neural Networks. Int. J. Control, 1990, 51(6): 1191～1214.
[69] Simon Haykin. Neural Networks: a Comprehensive Foundation [sencond edition].
[70] Rumelhart D. E., Hinton G. E., Williams R. J. Learning representations of back-propagation errors. Nature (London), 1986a, Vol. 323: 533～536.
[71] Rumelhart D. E., Hinton G. E., Williams R. J. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McCeland, eds., 1986b, vol 1, Chapter 8, Cambridge, MA: MIT Press.
[72] Rumelhart D. E., Zipser D. Feature discovery by competitive learning. Cognitive Science, 1985, 9: 75～112.
[73] 王文成.神经网络及其在汽车工程中的应用.北京理工大学出版社,1998.
[74] 袁曾任.人工神经元网络及其应用.清华大学出版社,2000.
[75] 杨秀坤.农产品品质检测中的人工智能方法研究.吉林工业大学博士学位 论文,1997.
[76] 楼顺天,施阳.基于MATLAB的系统分析与设计一神经网络.西安电子科技大学出版社,1999.
[77] 任露泉.试验优化技术.北京:机械工业出版社.
[78] David E. Goldberg. Genetic algorithms in Search, Optimization and Machine Learning. Addison-Wesley Pub. Co, 1989.
[79] Davis Lawrence. Handbook of Genetic Algorithms. Van Nostrand Reinhold, 1991.
[80] Goldberg, Santanic. Via GA, Pro. of 9th Conference on Electronic Computation. Eng. Opt, 1987 (9): 471～482.
[81] Hajala Lin CY. GA Strategies in multic-riterion optimal design. AIAA, 1991, 29(5): 1040～1046.
[82] Rajew. S, Krishanamoovthy. D. S. Discrete optimization of structures using Genetic Algorithms. Journal of Structural Engineering, 1992, 118(5):1233～ 1250.
[83] Holland J H. Adaptation in nature and artificial system. Ann Arbor: University of Michigan Press, 1975:11～14.
[84] Freeman L. M., et al. Turning fuzzy logic controller using genetic algorithms in aerospace applications. In Proceeing of the AAAIC'90 Conference, Dayton, Oct., 1990: 351～358.
[85] Glover F., et al. Genetic algorithms and tabu search: hybrids for optimization. Computer and Operation Research (UK), 1995, 122(1):111～134.
[86] McAulay A. D., Oh J. C. Improving learning of genetic rule-based classifier systems. IEEE Trans. On System, Man, and Cybernetics, 1994, 24(1):152～159.
[87] Matwin S., et al. Genetic algorithms approach to a negotiation support system. IEEE Trans. On Systems, Man and Cybernetics, 1991, 21 (1): 102～114.
[88] Qi, X. F., Palmieri E Adaptive mutation in the genetic algorithm. In Proceedings of the Second Annual Conference on Evolutionary. Programming. Fogel D. B., Atmar W., La Jolla (eds.), CA: Evolutionary Programming Society, 1993: 192～196.
[89] Chandrasekharam R., et al. Genetic algorithm for embedding a complete graph in a hypercube with a VLSI application. Micro-processing and Micro-programming, 1994, 40: 537～552.
[90] 李灏荃.遗传算法及神经网络在数据融合中的应用.西安电子科技大学硕士学位论文,1998.
[91] 李敏强等.遗传算法的基本理论与应用,北京:科学出版社.
[92] Whitley, L. D. (ed.) Foundations of genetic algorithms 2. San Mateo, CA: Morgan Kaufmann, 1993.
[93] Whitley L. D., Vose M. D. (eds.) Foundations of genetic algorithms 3. San Mateo, CA: Morgan Kaufmann, 1995.
[94] Melanie Mitchell. An introduction to genetic algorithms. Cambridge, MA: The MIT Press, 1996.
[95] Michalewicz Z. Genetic algorithm+Data structures=Evolution programs. AI Series. New York: Springer-Verlag, 1994.
[96] Holland J H. Genetic algorithm. Scientific American, July 1992, 253: 66.
[97] Jing K D. Learning with genetic algorithms: An overview. Machine Learning, 1988, 3: 121.
[98] Davis L. Handbook of genetic algorithms. 1st ed. Van Nostrand Reinhold, New York, 1991: 91～98.
[99] Goldberg D E. Genetic algorithm in search, optimization and machine learning. MA: Addison-Wesley Publishing Company, 1989
[100] De Jong, K. A. An analysis of the behavior of a class of genetic adaptive systems (Ph. D Dissertation). University of Michigan, No. 76～9381, 1975.
[101] Grefenstette, J. J. Optimization of control parameters for genetic algorithms. IEEE Transaction on Systems, Man, and Cybernetics, 1986, 16(1): 122～128.
[102] Schaffer, J. D. A study of control parameters affecting on-line performance of genetic algorithms for function optimization. In Proceedings of the Third International Conference on Genetic Algorithms (ICGA 3), Schaffer, J. D. (ed.), San Mateo, CA: Morgan Kaufmann Publishers, 1989:51～60.
[103] 王雪晶.彩色遥感图像的补偿与修正.中国科学院研究生院博士学位研究生学位论文,2002.
[104] 付建华.彩色打印机色彩空间转换方法研究.中国科学院研究生院硕士学位研究生学位论文,2004.