Spectral Characterization of Color Scanners Based on Principal Component Analysis

doi:10.7517/j.issn.1674-0475.2015.02.161

Imaging Science and Photochemistry ›› 2015, Vol. 33 ›› Issue (2): 161-167.DOI: 10.7517/j.issn.1674-0475.2015.02.161

Previous Articles Next Articles

Spectral Characterization of Color Scanners Based on Principal Component Analysis

YU Haiqi¹, LIU Zhen¹, TIAN Quanhui²

1. College of Communication and Art Design, University of Shanghai for Science and Technology, Shanghai 200093, P.R.China;
2. Shanghai Publishing and Printing College, Shanghai 200093, P.R.China

Received:2014-05-06 Revised:2014-08-15 Online:2015-03-15 Published:2015-03-15

Abstract

Abstract:

Spectral characterization of color scanners can achieve accurate obtaining of color information of scanners in the different light sources and observers. It can also avoid metamerism to the most extent. Spectral characterization was applied to characterize the color scanners. Principal component analysis, which was combined with polynomial regression and BP neural network technology, set up the nonlinear transformation relationship between the scanner RGB signal and spectral reflectance image information. Firstly, principal component analysis (PCA) was used to analyze the spectral reflectance of the training sample followed by the principal component scalars calculation and the spectral was represented by principal component times scalars of principal component. Conversion models for scalars of principal component and polynomial or BP neural network was built by experiments. The reflectance was built by RGB low-dimension signal and spectral characterization of color scanners was achieved. Experimental results showed that the better number of polynomial terms was 19, reaching the accuracy of 1.7% RMSE of training sample and 1.9% RMSE of test sample. And the optimum network structure was single hidden layer with 15 layer node, reaching the accuracy of 1.3% RMSE of training sample and 1.5% RMSE of test sample. The accuracy of polynomial regression method is much lower, which is not fit for spectral characterization. The BP neural network model may achieve higher spectral characterization accuracy.

Key words: color scanners, spectral characterization, polynomial regression, BP neural network, principal component analysis

YU Haiqi, LIU Zhen, TIAN Quanhui. Spectral Characterization of Color Scanners Based on Principal Component Analysis[J]. Imaging Science and Photochemistry, 2015, 33(2): 161-167.

References

[1] 徐艳芳,刘文耀,左坤隆,朱昊.彩色扫描仪的特征化.光学精密工程[J], 2004, 12(1):15-20. Xu Y F, Liu W Y, Zuo K L,Zhu H. Characterization of color scanners [J]. Optics and Precision Engineering, 2004, 12(1):15-20.
[2] 徐艳芳,黄敏,金杨.基于色度比特性的显示器色度特性化.液晶与显示[J]. 2008, 23(6):771-777. Xu Y F, Huang M, Jin Y. Characterization of monitors based on colorimetric ratios [J]. Journal of Liquid Crystals and Displays, 2008, 23(6):771-777.
[3] Kang H R. Color scanner calibration [J]. Journal of Imaging Science and Technology, 1992, 36(2):162-170.
[4] Johnson T. Methods for characterizing color scanners and digital cameras [J]. Displays, 16(4):183-191.
[5] Shi M, Healey G. Using reflectance models for color scanner calibration [J]. Journal of The Optical Society of America A, 2002, 19(4):645-656.
[6] Shen H L, Xin J H. Colorimetric and spectral characterization of a color scanner using local statistics [J]. Journal of Imaging Science and Technology, 2004, 48(4):342-346.
[7] Wang Y, Xu H S. Spectral characterization of scanner based on PCA and BP ANN [J]. Chinese Optics Letters, 2005, 3(12):725-728.
[8] Shen H L, Xin J H. Spectral characterization of a color scanner by adaptive estimation [J]. Journal of The Optical Society of America A, 2004, 21(7):1125-1130.
[9] 张显斗, 王强,杨根福, 武莉.光谱颜色管理系统关键技术综述[J].中国印刷与包装研究,2013,5(1):10-17. Zhang X D, Wang Q, Yang G F, Wu L. Key technologies review of the spectral color management system [J]. China Printing and Packing Study, 2013, 5(1):10-17.
[10] Tzeng D Y, Roy S B. A review of principal component analysis and its applications to color technology [J]. Color Research & Application, 2005, 30(2):84-98.
[11] Hong G,Luo M R, Rhodes P A.A study of digital camera colorimetric characterization based on polynomial modeling[J].Color Research and Application, 2001, 26(1):76-84.
[12] Vrhel M J, Trussell H J. Color scanner calibration via a neural network[C]. In:Proc.IEEE International Conference on Acoustics, Speech, and Signal Processing. Phoenix, USA:IEEE 1999, 3465-3468.

Spectral Characterization of Color Scanners Based on Principal Component Analysis

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics

Comments