摘要
颜色空间转换是色彩管理的核心技术,本课题利用EPSON STYLUS PRO9800喷墨打印机打样ECI2002标准随机色靶,选取建模和检验数据,进行CMYK与L~*a~*b~*颜色空间转换模型的研究,为色彩管理颜色空间转换提供更广泛的理论依据以及实践指导。
本课题依据四色平面理论,采用最小二乘法建立二元线性回归平面方程,通过相关性、显著性分析,验证了数码打样呈色符合四色平面规律。采用最小二乘法建立网点面积率与对应平面方程系数间的二次曲线方程,并将二次曲线方程代入选定K网点面积率的关于各色平面方程中初步得到选定K网点面积率时的转换方程,对其进行精度检验后确立K网点面积率分别为0%、20%、40%、60%、80%时的CMYK到L~*a~*b~*颜色空间转换方程。采用三次样条插值算法建立选定K网点面积率与对应转换方程中各项系数之间的关系,得到任意K网点面积率时CMYK到L~*a~*b~*颜色空间的正向转换方程,并分析了方程精度。
依据BP神经网络理论、GA-BP神经网络理论,按各色块心理明度L~*测量值划分建模数据,确定10段相同结构的BP神经网络并进行训练;考虑到BP神经网络初始权值随机性会影响网络精度及速度等问题,利用遗传算法(GA)优化各段BP神经网络的权值和阈值,作为BP神经网络的初始值进行再训练,经过对比分析,发现经GA优化后的BP神经网络在速度和精度的实现上比单纯的BP神经网络好,同时建立了L~*a~*b~*到CMYK颜色空间的BP神经网络以及GA-BP神经网络反向转换模型。
基于数码打样正反转换模型的建立过程为各类印刷方式下色彩管理的颜色空间转换方法提供了更多的参考,具有一定的指导意义。
The conversions of color spaces are core technique of color management.The purpose of topic is doing the research about the models of conversion between CMYK and L~*a~*b~* that provides wider theory basis and practical guide on the basis of printing the standard color target ECI2002 obtained from inkjet printer named EPSON STYLUS PRO9800,and choosing the data of building and checking.
According to plane theory of four colors,the topic verifies the plane regulation of Digital Proofing paper about four colors by establishment of binary linear regression plane equation built by least-squares method and analyses of equations' correlation and variance.The quadratic curve equations about relation between dot area and the coefficient of each plane equation are built by least-squares method and then are substituted into the coefficient of plane equations. The conversion equations are initially gained.The conversion equations under given K dot areas with 0%、20%、40%、60%、80%from CMYK to L~*a~*b~* color space can be gotten after check of initial conversion equations' accuracy.After the relation between K with 0%、20%、40%、60%、80%and each coefficient of conversion equation are found,the positive conversion equation at every K from CMYK to L~*a~*b~* color spaces are built by using cubic spline interpolation algorithm and the accuracy of equations are analyzed.
According the theory of BP and GA-BP Neural Network,the data of building model are differentiated by measuring L~* to train ten BP Neural Network with same structure.Because of the random of initial weights in BP Neural Network,the topic uses GA to research best weights and bios of each BP Neural Network in order to apply to BP Neural Network and to retrain BP Neural Network.Through contrast of BP and GA-BP Neural Network,it can be found that GA-BP is better than BP at training speed and accuracy.At the same time,the reverse conversion models of BP and GA-BP Neural Network are built.
The process building conversions of color spaces based on Digital Proofing provides more references for the conversion methods between two color spaces of color management under different printing types,which has practical meaning.
引文
[1]胡涛,汪鑫.浅谈开放式色彩管理[J].今日印刷,2004,(4):41-42
[2]李举.调频加网呈色模型与分色配色模型的研究[D].西安:西安理工大学,2006
[3]Guenter Bestmann.Technical Recommendation Color Characterization Target and Data File Format For 4-printing[R/OL].http://www.eci.org/eci/en/060_downloads.php,2001-11-26
[4]Brace Fraser Chris Murphy Fred Bunting.Real World Color Management[M].北京:电子工业出版社,2005
[5]王胜.数码打样中的色彩管理实施方案[J].今日印刷,2004,(2):33-36
[6]刘全香.数字印刷技术[M].北京:印刷工业出版社,2006:112-191
[7]梁静,张立辉.数码打样色彩管理系统的研究[J].包装工程,2006,(6):108-112
[8]Michael Has-FOGRA,Todd Newman-SGI.Color Management:Current Practice and the Adoption of a New Standard[J].TAGA,1995:748-750
[9]Wang Xiao-hua.Color control of the multi-color printing device[J].Zhejiang University SCIENCE A.2006,7(7):1187-1192
[10]田玉敏,梁若莹.计算机彩色输入输出设备常用颜色空间及其转换[J].计算机工程,2002,(9):198-200
[11]胡成发.印刷色彩与色度学[M].北京:印刷工业出版社,1993:174-178
[12]松妍.色彩管理及其应用[J].今日印刷,2005,(5):4-7
[13]刘世昌.印品质量检测与控制[M].北京:印刷工业出版社,2000:29-32
[14]周世生.高等色彩学[M].北京:印刷工业出版社,1997:117-126
[15]景翠宁.基于ICC的标准的输出设备的色彩管理研究[D].西安:西安理工大学,2003
[16]Henry R.Kang.Color Technology for Electronic Imaging Devices[C].SPIE:Optical Engineering Press,1996
[17]Henry R.Kang.Color scanner calibration of reflected samples[J].Proc.SPIE:Color Hard Copy and Graphic Arts,1992,1670:468-477
[18]胡涛,张志刚,张晓燕.基于ICC标准的扫描仪色彩管理研究[J].西安理工大学学报,2004,20(1):40-43
[19]许宝卉,李言,薛红.基于色彩管理的CRT色彩空间转换方法的研究[J].液晶与显示,2007,22(3):351-354
[20]周瑞.彩色数码相机色彩空间转换模型的研究[D].西安:西安理工大学,2007
[21]G.Hong,M.R.luo,et.A Study of Digital Camera Colorimetric Characterization Based on Polynomial Modeling[J].Color Res and Appl,2001,26(1):76-84
[22]付建华.彩色打印机色彩空间转换方法研究[D].北京:中国科学院研究生院,2004
[23]Henry R.Kang.Comparisons of three-dimensional interpolation techniques by simulations[J].Proc.SPIE 1995,2414:104-114
[24]张晓燕..基于ICC标准的色彩管理系统研究——输入设备特性研究及特征描述文件建立[D].西安:西安理工大学,2000
[25]Sigfredo I.Nin,James M.Kasson,Wil Plouffe.Printing CIELAB images on a CMYK printer using tri-linear interpolation[J].SPIE:Color Hard Copy and Graphic Arts,1992,1670:316-324
[26]史瑞芝.用查表插值法实现CIELab与CMYK颜色空间的转换[J].测绘学院学报,2002,(9):224-226
[27]阎凡平,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2005:593-599
[28]郭茂祖,王亚东,苏晓红,王兴起.基于BP网络的色彩匹配方法研究[J].计算机学报,2000,23(8):819-823
[29]张燕,张二虎.初探色彩管理中的色空间转换技术[J].中国印刷,2002,(9):75-77
[30]M.J.Vrhel,H.J.Trussell.Color Scanner Calibration via Neural Network[J].IEEE ICASSP,1999,6:3465-3468
[31]胡涛,刘睿,张志刚.基于BP网络的扫描仪色彩空间转换[J].印刷杂志,2003,(3):43-44
[32]LiaoNingfang,Gaozhiyun.A Comparative Study of a CRT Colorimetric Predition Model by Neural Networks and the Models by Conventional Method[J].Color Research &Application,1999,24(1):45-51
[33]王歆平.基于ICC标准色彩管理系统研究-显示设备特征研究及特征描述文件的建立[D].西安:西安理工大学,2000
[34]Shoji Tominaga.Color control of printers by neural networks[J].Journal of Electronic Imaging 1998,7(3):664-671
[35]MITSUO KAJI,YOSHIHIKO AZUMA,MICHITAKA NONAKA.Some Colorimetric Properties included in the Color Characterization Data of Process Prints[J].TAGA,1998:226-241
[36]杜春燕.柔版印刷中平面呈色理论的研究[D].西安:西安理工大学,2007
[37]何侠.智能卡彩色印刷呈色数学模型[D].西安:西安理工大学,2007
[38]Cao Congjun,Zhou Mingquan,Xu Jinlin.Research on Equation from L~*a~*b~* to CMY[J].仪器仪表学报,2004,(8):129-133
[39]徐敏.L~*a~*b~*到CMY转换方程的研究[D].西安:西安理工大学硕士论文,2003
[40]康一.L~*a~*b~*到CMYK色彩空间转换方程的研究[D].西安:西安理工大学,2006
[41]徐锦林,闫小凡,徐宏平,徐咏驰.喷墨印刷平面呈色模型的建立与检验[J].武汉大学学报,2006,31(9):822-825
[42]陈国良,王熙法等.遗传算法及其应用[M].北京:北京人民邮电出版社,1996
[43]吴景岚.一个遗传神经网络预测模型[J].闽江学院学报,2004,(4):52-56
[44]闵涛,秦新强,赵凤群.数值分析[M].北京:中国科学文化出版社,2003:41-42
[45]周双全,赵达尊.基于BP神经网络打印机色彩控制技术[J].光学技术,2000,26(1):49-51
[46]赵艳东.如何控制与评价数码打样的色彩再现[J].今日印,2005,(3):53-55
[47]M.R.斯皮格,J.希勒 R.A.斯里尼瓦桑.概率与统计[M].北京:科学出版社,2002:209-214
[48]Morris H.D eGroot,Mark J.Schervish.概率统计[M].北京:人民邮电出版社,2007:367-374
[49]胡细宝,孙洪祥,王丽霞.概率论.数理统计.随机过程[M].北京:北京邮电大学出版社,2004:374-378,514-522
[50]Kelvin Tritton.印刷色彩控制手册[M].北京:印刷工业出版社,2006:30
[51]王沫然.MATLAB与科学计算[M].北京:北京电子工业出版社,2004:225-227
[52]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版,1995:6-10
[53]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005:69
[54]胡守仁,余少波,戴葵.神经网络导论[M].长沙:国防科技大学出版社,1993:113-116
[55]罗天晴.基于BP神经网络的企业股权价值评估研究[D].长沙:中南大学,2007
[56]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1994:212-216
[57]D.Montana,L.Davis.Training Feed forward Neural Networks Using Genetic Algorithms[J].Proceedings of the International Joint Conference on Artificial Intelligence,1989
[58]苑希民,李鸿雁,刘树坤,崔广涛.神经网络和遗传算法在水科学领域的应用[M].北京:中国水利水电出版社,2002
[59]A.S.Cofifio,J.M.Gutierrez,M.L.Ivanissevich.Evolving modular networks with genetic algorithms:application to nonlinear time series[J].Ivanissevich,M.L.ExpertSystem,2004,21(4):208-216
[60]雷英杰,张善文,李续武,周创明.MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社,2005:3-4,146-192
[61]余正红,李志博,尹朝庆.基于遗传神经网络的货运量的研究与实现[J].交通与计算机,2006,24(5):93-95
[62]郭彬生,刘伟铭,姜山.基于遗传神经网络的道路交通量预测[J].广西交通科技,2003,28(2):24-26
[63]Bramlette M F.Initialization,Mutation and Selection Methods in Genetic Algorithms for Function Optimization[J].Proc ICGA 4,1991:100-107
[64]李显宏.MATLAB 7.X界面设计与编译技巧[M].北京:电子工业出版社,2006:226