[1] Wang Ying, Zeng Ping, Luo Xuemei, et al. Low-dimensional multi-spectral space for color reproductionbased on nonnegative constrained principal component analysis [J]. Journal of Southeast University (English Edition), 2009, 25 (4): 486-490. [doi:10.3969/j.issn.1003-7985.2009.04.015]

Copy

Low-dimensional multi-spectral space for color reproductionbased on nonnegative constrained principal component analysis()

基于非负主成分分析的低维光谱色彩空间表示法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

25

Issue:

2009 4

Page:

486-490

Research Field:

Information and Communication Engineering

Publishing date:

2009-12-30

Info

Title:

Low-dimensional multi-spectral space for color reproductionbased on nonnegative constrained principal component analysis

基于非负主成分分析的低维光谱色彩空间表示法

Author(s):

Wang Ying¹, Zeng Ping^{1, 2}, Luo Xuemei¹, Xie Kun¹

¹School of Computer Science and Technology, Xidian University, Xi’an 710071, China
²School of Computer Science, Xi’an Shiyou University, Xi’an 710065, China

王莹¹, 曾平^{1, 2}, 罗雪梅¹, 谢琨¹

¹西安电子科技大学计算机学院, 西安 710071; ²西安石油大学计算机学院, 西安 710065

Keywords:

spectral color science;  nonnegative constrained principal component analysis;  low-dimensional spectral space;  nonlinear optimization;  multi-spectral images;  spectral reflectance

光谱色彩学;  非负约束主成分分析;  低维光谱空间;  非线性优化;  多光谱图像;  光谱反射比

PACS:

TN911.74;TP301.6

DOI:

10.3969/j.issn.1003-7985.2009.04.015

Abstract:

In order to overcome the shortcomings that the reconstructed spectral reflectance may be negative when using the classic principal component analysis(PCA)to reduce the dimensions of the multi-spectral data, a nonnegative constrained principal component analysis method is proposed to construct a low-dimensional multi-spectral space and accomplish the conversion between the new constructed space and the multi-spectral space. First, the reason behind the negative data is analyzed and a nonnegative constraint is imposed on the classic PCA. Then a set of nonnegative linear independence weight vectors of principal components is obtained, by which a low-dimensional space is constructed. Finally, a nonlinear optimization technique is used to determine the projection vectors of the high-dimensional multi-spectral data in the constructed space. Experimental results show that the proposed method can keep the reconstructed spectral data in [0, 1]. The precision of the space created by the proposed method is equivalent to or even higher than that by the PCA.

针对采用主成分分析法进行多光谱数据降维会使重构光谱反射比出现负值的问题, 提出一种非负约束主成分分析法, 并用该法构造低维空间, 实现高维多光谱数据向低维空间的转换. 首先分析主成分分析法产生非光谱数据的原因, 据此对经典主成分分析模型增加非负约束; 然后求出一组线性无关的非负主成分权向量, 用该组向量构造低维空间; 最后用非线性优化技术确定高维数据在该低维空间中的投影值, 实现了高维空间与低维空间的相互转换. 实验结果表明, 新方法能使重构光谱数据在[0, 1]内, 保持了光谱反射比的物理意义, 同时所构造低维空间的精度能与经典主成分分析法保持一致.

References:

[1] Zhao Yonghui, Berns S R, Taplin A L, et al. An investigation of multispectral imaging for the mapping of pigments in paintings[C]//Proceedings of International Society for Optical and Photonics Engineering. San Jose, CA, USA, 2008, 6810: 681007-1-9.
[2] Bochko V, Tsumura N, Miyake Y. A spectral color imaging system for estimating spectral reflectance of paint[J]. Journal of Imaging Science and Technology, 2007, 51(1): 70-78.
[3] Munzenmayer C, Paulus D, Wittenberg T. A spectral color correction framework for medical applications[J]. IEEE Trans on Biomedical Engineering, 2006, 53(2): 254-265.
[4] Tsummura N, Miyake Y, Imai H F. Medical vision: measurement of skin absolute spectral-reflectance-image and the application to component analysis[C]//Proceedings of the 3rd Int Conf on Multispectral Color Science. Joensuu, Finland, 2001: 25-28.
[5] Wu Chungyi, Lee Shunming, Wen Chaohua, et al. Multi-spectral image acquisition system for color spectrum reproduction[C]//Proceedings of the 16th IPPR Conf on Computer Vision, Graphics and Image Processing. Kinmen, Taiwan, China, 2003: 115-122.
[6] Bakke M A, Farup I, Hardeberg Y J. Multispectral gamut mapping and visualization—a first attempt[C]//Proceedings of International Society for Optical and Photonics Engineering. San Jose, CA, USA, 2005, 5667: 193-200.
[7] Yu Shanshan, Murakami Y, Obi T, et al. Multispectral image compression for improvement of colorimetric and spectral reproducibility by nonlinear spectral transform[J]. Optical Review, 2006, 13(2): 346-356.
[8] Yu Shanshan, Murakami Y, Obi T, et al. Improvements for multispectral image compression for color reproducibility with preservation to spectral accuracy[C]//IEEE Int Conf on Image Processing. Genova, Italy, 2005: 710-713.
[9] Derhak W M, Rosen R M. Spectral colorimetry using LabPQR: an interim connection space[J]. Journal of Imaging Science and Technology, 2006, 50(1): 53-63.
[10] Tsutsumi S, Rosen R M, Berns S R. Spectral color management using interim connection spaces based on spectral decomposition[C]//Proceedings of the 14th Color Imaging Conf. Arizona, USA, 2006: 246-251.
[11] Imai H F, Rosen R M, Berns S R. Comparative study of metrics for spectral match quality[C]//Proceedings of the First European Conference on Color Graphics, Imaging, and Vision. Poitiers, France, 2002: 492-496.

Memo

Memo:

Biographies: Wang Ying(1977—), female, graduate; Zeng Ping(corresponding author), male, professor, zp8637@126.com.
Foundation items: The Pre-Research Foundation of National Ministries and Commissions(No.9140A16050109DZ01), the Scientific Research Program of the Education Department of Shanxi Province(No.09JK701).
Citation: Wang Ying, Zeng Ping, Luo Xuemei, et al. Low-dimensional multi-spectral space for color reproduction based on nonnegative constrained principal component analysis[J]. Journal of Southeast University(English Edition), 2009, 25(4): 486-490.

Common functions