摘要
现代先进的ICC色彩管理技术,是以色彩空间变化为核心的新型色彩控制方法,其中CMYK和L*a*b*颜色空间的转换在色彩管理中具有广阔的理论研究价值和实用价值。课题基于数码打样实验,输出在Photoshop中设计的色靶,选取建模数据和检验数据,基于平面理论建立CMYK到L*a*b*颜色空间的正向转换模型;分别基于GA—BP神经网络、广义回归神经网络(GRNN)建立L*a*b*到CMYK颜色空间反向转换模型。
依据四色网点的平面呈色规律,利用数理统计中的二元线性回归的方法建立K网点面积率以及CMY某一彩色网点面积率一定,其他两彩色网点面积率变化的平面方程,再利用最小二乘抛物线法得到平面方程每个系数与网点面积率的二次拟合曲线,最终建立起K网点面积率分别为0%,10%,20%,30%,40%,50%,60%,70%,80%,85%,90%,95%,98%的颜色空间转换方程。经过色差分析,发现特定K值下颜色空间转换方程具有较高精度,且K=50%以后的转换方程比K=50%以前的方程转换精度高,这可能是因为亮调区域受测量值精度的影响。然后通过三次样条插值算法,建立起任意的K网点面积率下的颜色空间转换方程,方程也可达到较高精度,且其精度受特定K值下颜色空间转换方程精度的影响。因此增加网点面积率K=50%以后的数据,基于平面理论可以实现任意K网点面积率下CMYK到L*a*b*颜色空间更精确的转换。
采用GA—BP神经网络建立颜色空间反向转换模型时,隐层和隐层神经元数的确定和调整过程很繁琐,且模型的预测精度不高,因此GA—BP神经网络应用于L*a*b*到CMYK的转换还是存在不少问题的。而基于GRNN进行的颜色模型变换研究可知该网络在学习样本确定后,则相应的网络结构和各神经元之间的连接权值也随之确定,网络的训练实际上只需确定SPREAD值,网络训练速度快、容易实现且模型的精度较高。
The conversions of color spaces are core technique of modern ICC color management and the study of color space conversion algorithm between L*a*b* and CMYK is value both in theory and application. The building and testing data are obtained by outputting target designed in Photoshop based on digital proofing. The forward color space conversion model between CMYK and L*a*b* is based on plane theory and the reverse models are based on BP Neural Network and Generalized Regression Neural Network respectively.
According to plane theory of four colors the plane equation is build by binary linear regression method. Then the quadratic curve equations about relation between the coefficient of each plane equation and dot area are built by least-squares method. The conversion equations under given K dot areas with 0%,10%,20%,30%,40%,50%,60%,70%,80%,85%, 90%,95%,98% are gained. After computation it can be found that the conversion equations under given K dot areas have high accuracy and the equations after K=50% have higher accuracy than those before K=50% which is probably because the light area is affected by measure data. Finally the conversion equations at every K from CMYK to L*a*b* color spaces are built by using cubic spline interpolation algorithm and they also have high accuracy which is affected by accuracy of equations under given K.
The number of hidden layers and neurons of hidden layers are difficult to decide when reverse model is built based on GA-BP Neural Network. And the model has poor accuracy so there are many problems of building reverse model based on GA-BP Neural Network. The study of reverse model based on GRNN shows that if the building data is determined the corresponding network is also determined and the training of network is the process to determine the SPREAD value. GRNN grains an advantage over GA-BP network weather in training conveniency, speed or precision.
引文
[1]周世生,郑元林,曹从军,戚永红.印刷色彩学[M].北京:印刷工业出版社,2005:3-6
[2]谭青.色彩管理在印前打样的意义—浅析软打样与数码打样的对比[J].广东印刷,2007,(4):17-21
[3]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
[4]杨净.数字印刷及应用[M].北京:化学工业出版社,2005:26-39
[5]刘全香.数字印刷技术[M].北京:印刷工业出版社,2006:181-192
[6]田全慧,刘珺.印刷色彩管理[M].北京:印刷工业出版社,2003:50-66
[7]Lindsay W MacDonald. Developments in colour management systems[J]. Displays,1996, (16): 203-211
[8]熊凯.计算机输入输出设备的色彩管理系统研究[D].西安:西安理工大学,2005
[9]景翠宁.基于ICC标准的输出设备的色彩管理的研究[D].西安:西安理工大学,2002
[10]International Color Consortium.Specification ICC[EB/OL]. http://www.color.org/ICClv42_2006-05.pdf,2004-10
[11]黄庆梅,赵达尊.彩色复制中的色域映射[J].照明工程学报,2002,(13):19-26
[12]GLrogers. Neugebauer revisited:random dots in halfone screening[J]. Color research and application.1998, (23):104-113.
[13]胡成发.印刷色彩与色度学[M].北京:印刷工业出版社,1993:20-32
[14]周世生.高等色彩学[M].北京:印刷工业出版社,1997:117-126
[15]刘世昌.印刷品质量检测与控制[M].北京:印刷工业出版社,2000:29—32
[16]Henry R.Kang. Color Technology for Electronic Imaging Devices[M]. SPIE Optical Engineering Press,1996
[17]Liu Haoxue. A Method of Computing Scanner's Spectral Response Curves[J].仪器仪表学报, 2004,25(4):39-43.
[18]Henry R.Kang. Color scanner calibration of reflected samples. SPIE.Color Hard Copy and Graphic Arts,1992,1670:468-477.
[19]G.Hong, M.R.luo, et. A Study of Digital Camera Colorimetric Characterization Based on Polynomial Modeling. Color Research and Application,2001,26(1):76-84.
[20]Sigfredo I.Nin, James M.Kasson,Wil Plouffe Printing CIELAB images on a CMYK printer using tri-linear interpolation. SPIE:Color Hard Copy and Graphic Arts,1992,1670:316-324.
[21]史瑞芝.用查表插值法实现CIEL*a*b*与CMYK颜色空间的转换[J].测绘学院学报,2002,19(3):224-226.
[22]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
[23]李艳妮.L*a*b*与CMYK转换方程的研究[D].西安:西安理工大学,2007
[24]M.J.Vrhel, H.J.Trussell. Color Scanner Calibration via a Neural Network.IEEE.1999(6):3465-3468
[25]Shoji Tominaga. Color control of printers by neural networks.Journal of Electronic Imaging.1998(3): 664-671.
[26]阎平凡,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,2005:26-34.
[27]周祎.基于数码打样CMYK到L*a*b*颜色空间转换的研究[D].西安:西安理工大学,2008
[28]Mitsuo KAJI,Yoshihiko AZUMA,Michitaka NONAKA.Some Colorimetric Properties included in the Color Characterization Data of Process Prints[J].TAGA.1998:226-232.
[29]徐敏.L*a*b*到CMY转换方程的研究[D].西安:西安理工大学,2003.
[30]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,2007.
[31]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,2006.
[32]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.
[33]Cao Congjun, Zhou Mingquan, Xu Jinlin.Research on Equation from L*a*b* to CMY[J].仪器仪表学报,2004,25(4):129-133.
[34]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.武汉大学学报,2006,31(9):822-825
[35]关治,陆金甫.数值分析基础[M].北京:高等教育出版社,2002:126-130
[36]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
[37]M.R.斯皮格,J.希勒R.A.斯里尼瓦桑.概率统计[M].北京:科学出版社,2002:209-214
[38]董霖.MATLAB使用详解[M].北京:科学出版社,2008:401-404
[39]张良均.曹晶.蒋世忠.神经网络实用教程[M].北京:机械工业出版社,2008:77-81
[40]John F.Kolen,Jordan B.Pollack.Back Propagation is Sensitive to Initial Conditions[J]. Technical Report TR 90-JK-BPSIC,1990.
[41]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
[42]D.Montana and L. Davis, Training Feedforward Neural Networks Using Genetic Algorithms. Proceedings of the International Joint Conference on Artificial Intelligence.1989
[43]李敏强,徐博艺,寇纪淞.遗传算法与神经网络的结合[J].系统工程理论与实践,1999,2:65-69
[44]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
[45]飞思科技产品研发中心.神经网络理论与MATLAB 7实现.北京:电子工业出版社.2005:17,123
[46]王春玲.基于径向基函数网络的非线性系统自适应逆控制[D].济南:山东大学2007
[47]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007:20-25
[48]卢慧敏,李大磊,覃寿同,孟令启.基于GRNN神经网络的中厚板轧机宽展预测模型[J].机械制造,2007,45(511):20-23
[49]Specht D F. A general regression neural network [J]. IEEE Tras Neural Networks,1991,2(6): 568-576.
[50]郝鑫.广义回归神经网络和遗传算法研究及其在化工过程建模中的应用[D].杭州:浙江大学,2004
[51]罗毅.基于灰色理论与广义回归神经网络的客运量预测模型[D].成都:西南交通大学,2007