基于样本选择的光谱重构研究
|
摘要
目的为了提高使用主成分分析法重构光谱反射率的重构精度。方法利用Matlab进行仿真实验,选择3种不同色卡作为训练样本,使用主成分分析法探究主成分个数和样本间隔对重构结果的影响。结果主成分个数为4时,贡献率均超过99%;样本间隔为10 nm时,RC24色卡重构效果最好,其平均色差2.37ΔE_(ab)~*平均均方根误差为0.0185。结论训练样本的选择会影响光谱重构精度,RC24色卡具有数据量小、重建精度较高的特点,在颜色复制领域可以优先选择。
The work aims to improve the reconstruction accuracy of spectral reflectance with principal component analysis(PCA). Matlab was used to conduct simulation experiments. 3 different color cards were selected as the training samples and the effect of the number of principal components and the sample interval on the reconstruction results was investigated by the method of PCA. When the number of principal components was 4, the contribution rate was over 99%. When the sample interval was 10 nm, the RC24 color card had the best reconstruction effect, its average color difference was 2.37 ΔE_(ab)~* and the average root-mean-square error was 0.0185. The selection of training samples will affect the accuracy of spectral reconstruction. With the characteristics of small amount of data and high accuracy of reconstruction, RC24 color card can be preferred in the field of color reproduction.
The work aims to improve the reconstruction accuracy of spectral reflectance with principal component analysis(PCA). Matlab was used to conduct simulation experiments. 3 different color cards were selected as the training samples and the effect of the number of principal components and the sample interval on the reconstruction results was investigated by the method of PCA. When the number of principal components was 4, the contribution rate was over 99%. When the sample interval was 10 nm, the RC24 color card had the best reconstruction effect, its average color difference was 2.37 ΔE_(ab)~* and the average root-mean-square error was 0.0185. The selection of training samples will affect the accuracy of spectral reconstruction. With the characteristics of small amount of data and high accuracy of reconstruction, RC24 color card can be preferred in the field of color reproduction.
引文
[1]龙艳群,王慧琴,王可,等.基于样本优化选取的光谱重建方法研究[J].影像科学与光化学,2017,35(1):88—96.LONG Yan-qun,WANG Hui-qin,WANG Ke,et al.Study on Spectral Reconstruction Method Based on Optimized Selected Samples[J].Imaging Science and Phorochemistry,2017,35(1):88—96.
[2]兑利涛.多光谱图像的光谱反射率重建技术研究[D].南昌:华东交通大学,2017.DUI Li-tao.Spectral Reflectance Reconstruction of Multispectral Images[D].Nanchang:East China Jiaotong University,2017.
[3]WANG H W,LI J,CHEN G X.Study on Key Issues of Multi-spectral Color Reproduction Technique[J].Advanced Materials Research,2011,174:93—96.
[4]ZHU Y,LI B,XU X.Spectral Reconstruction and Accuracy Appraisal Based on Pseudo Inverse Method[C]//Photonics and Optoelectronics(SOPO),2012 Symposium on IEEE,2012:1—3.
[5]梁金星,万晓霞,王琪.光谱重建训练样本选择方法研究[J].包装工程,2016,37(7):125—130.LIANG Jin-xing,WAN Xiao-xia,WANG Qi.Selection Method of Training Samples for Spectral Reconstruction[J].Packaging Engineering,2016,37(7):125—130.
[6]HARIFI T,AMIRSHAHI S,AGAHIAN F.Recovery of Reflectance Spectra from Colorimetric Data Using Principal Component Analysis Embedded Regression Technique[J].Optical Review,2008,15(6):302—308.
[7]SONG J,KIM C,YOO Y.Vein Visualization Using a Smart Phone with Multispectral Wiener Estimation for Point-of-care Applications[J].Biomedical&Health Informatics IEEE Journal of,2015,19(2):773—778.
[8]陈奕艺,徐海松,张显斗,等.基于数码相机的光谱重构研究[J].光学学报,2009,29(5):1416—1419.CHEN Yi-yi,XU Hai-song,ZHANG Xian-dou,et al.Study of Spectral Reconstruction Based on Digital Camera[J].Acta Optica Sinica,2009,29(5):1416—1419.
[9]何成栋,黄新国,张姗姗.基于颜色属性的光谱重建训练样本正交优化[J].包装学报,2016,37(3):66—70.HE Cheng-dong,HUANG Xin-guo,ZHANG Shan-shan.Orthogonal Optimization of Spectral Reconstruction Training Samples Based on Color Properties[J].Packaging Journal,2016,37(3):66—70.
[10]于海琦,刘真,张雷洪,等.样本特征对光谱图像重构影响的研究[J].包装工程,2014,35(13):144—149.YU Hai-qi,LIU Zhen,ZHANG Lei-hong,et al.Effects of Sample Characteristics on Spectral Image Reconstruction[J].Packaging Engineering,2014,35(13):144—149.
[11]李天一.实际物体色色域的研发[D].鞍山:辽宁科技大学,2016.LI Tian-yi.The Development of The Real Object Colour Gamut[D].Anshan:University of Science and Technology Liaoning,2016.
[12]ZHANG Y,ZHOU S S.Research on Reconstruction of Spectral Reflectance Based on Principal Component Analysis[J].Applied Mechanics and Materials,2013,262:53—58.
[13]JING X,YUE T X,ZHENG L.Research on Spectral Reflectance Reconstruction Algorithms for Munsell Color Card[M].Springer India,2014.
[14]SHAMS-NATERI A.Wavelength Intervals Effect on Reflectance Spectra Reconstruction[J].Optica Applicata,2012,42(4):737—742.
[15]ZHANG X D,WANG Q,LI J C,et al.The Interim Connection Space Based on Human Color Vision for Spectral Color Reproduction[J].Optical Society of America.Journal A:Optics,Image Science,and Vision,2012,29(6):1027.
[2]兑利涛.多光谱图像的光谱反射率重建技术研究[D].南昌:华东交通大学,2017.DUI Li-tao.Spectral Reflectance Reconstruction of Multispectral Images[D].Nanchang:East China Jiaotong University,2017.
[3]WANG H W,LI J,CHEN G X.Study on Key Issues of Multi-spectral Color Reproduction Technique[J].Advanced Materials Research,2011,174:93—96.
[4]ZHU Y,LI B,XU X.Spectral Reconstruction and Accuracy Appraisal Based on Pseudo Inverse Method[C]//Photonics and Optoelectronics(SOPO),2012 Symposium on IEEE,2012:1—3.
[5]梁金星,万晓霞,王琪.光谱重建训练样本选择方法研究[J].包装工程,2016,37(7):125—130.LIANG Jin-xing,WAN Xiao-xia,WANG Qi.Selection Method of Training Samples for Spectral Reconstruction[J].Packaging Engineering,2016,37(7):125—130.
[6]HARIFI T,AMIRSHAHI S,AGAHIAN F.Recovery of Reflectance Spectra from Colorimetric Data Using Principal Component Analysis Embedded Regression Technique[J].Optical Review,2008,15(6):302—308.
[7]SONG J,KIM C,YOO Y.Vein Visualization Using a Smart Phone with Multispectral Wiener Estimation for Point-of-care Applications[J].Biomedical&Health Informatics IEEE Journal of,2015,19(2):773—778.
[8]陈奕艺,徐海松,张显斗,等.基于数码相机的光谱重构研究[J].光学学报,2009,29(5):1416—1419.CHEN Yi-yi,XU Hai-song,ZHANG Xian-dou,et al.Study of Spectral Reconstruction Based on Digital Camera[J].Acta Optica Sinica,2009,29(5):1416—1419.
[9]何成栋,黄新国,张姗姗.基于颜色属性的光谱重建训练样本正交优化[J].包装学报,2016,37(3):66—70.HE Cheng-dong,HUANG Xin-guo,ZHANG Shan-shan.Orthogonal Optimization of Spectral Reconstruction Training Samples Based on Color Properties[J].Packaging Journal,2016,37(3):66—70.
[10]于海琦,刘真,张雷洪,等.样本特征对光谱图像重构影响的研究[J].包装工程,2014,35(13):144—149.YU Hai-qi,LIU Zhen,ZHANG Lei-hong,et al.Effects of Sample Characteristics on Spectral Image Reconstruction[J].Packaging Engineering,2014,35(13):144—149.
[11]李天一.实际物体色色域的研发[D].鞍山:辽宁科技大学,2016.LI Tian-yi.The Development of The Real Object Colour Gamut[D].Anshan:University of Science and Technology Liaoning,2016.
[12]ZHANG Y,ZHOU S S.Research on Reconstruction of Spectral Reflectance Based on Principal Component Analysis[J].Applied Mechanics and Materials,2013,262:53—58.
[13]JING X,YUE T X,ZHENG L.Research on Spectral Reflectance Reconstruction Algorithms for Munsell Color Card[M].Springer India,2014.
[14]SHAMS-NATERI A.Wavelength Intervals Effect on Reflectance Spectra Reconstruction[J].Optica Applicata,2012,42(4):737—742.
[15]ZHANG X D,WANG Q,LI J C,et al.The Interim Connection Space Based on Human Color Vision for Spectral Color Reproduction[J].Optical Society of America.Journal A:Optics,Image Science,and Vision,2012,29(6):1027.