面向色彩再现的多光谱图像非线性降维方法

王莹; 王忠民; 王义峰; 罗雪梅

doi:10.3788/OPE.20111905.1171

您当前的位置：

首页 >

文章列表页 >

面向色彩再现的多光谱图像非线性降维方法

信息科学 | 更新时间：2020-08-12

- 面向色彩再现的多光谱图像非线性降维方法
- Nonlinear dimensionality reduction of multi-spectral images for color reproduction
- 光学精密工程 2011年19卷第5期页码：1171-1178
- 作者机构：
  
  1. 西安邮电学院计算机学院,陕西西安,710121
  2. 西安电子科技大学计算机外部设备研究所,陕西西安,710071
- 作者简介：
- 基金信息：
  
  国家部委"();十一五"();预研项目(No.51316060203)();国家部委预研基金资助项目(No.9140A16050109DZ01)()
- DOI：10.3788/OPE.20111905.1171
  中图分类号： O432.3;TP391.4
- 收稿日期：2010-09-13，
  
  修回日期：2010-10-27，
  
  网络出版日期：2011-05-26，
  
  纸质出版日期：2011-05-26
- 稿件说明：
移动端阅览
王莹, 王忠民, 王义峰, 罗雪梅. 面向色彩再现的多光谱图像非线性降维方法[J]. 光学精密工程, 2011,19(5): 1171-1178

WANG Ying, WANG Zhong-min, WANG Yi-feng, LUO Xue-mei. Nonlinear dimensionality reduction of multi-spectral images for color reproduction[J]. Editorial Office of Optics and Precision Engineering, 2011,19(5): 1171-1178
王莹, 王忠民, 王义峰, 罗雪梅. 面向色彩再现的多光谱图像非线性降维方法[J]. 光学精密工程, 2011,19(5): 1171-1178 DOI： 10.3788/OPE.20111905.1171.

WANG Ying, WANG Zhong-min, WANG Yi-feng, LUO Xue-mei. Nonlinear dimensionality reduction of multi-spectral images for color reproduction[J]. Editorial Office of Optics and Precision Engineering, 2011,19(5): 1171-1178 DOI： 10.3788/OPE.20111905.1171.

摘要

针对多光谱图像数据维数高导致图像色彩再现过程中数据处理复杂度高的问题

提出一种多光谱图像非线性降维方法。首先根据人眼视觉系统特征

用CIE标准观察者色匹配函数对源光谱进行加权

对加权光谱采用主成分分析(PCA)方法降维来提高降维的色度精度及光照变换时的色差稳定性;然后针对因色匹配函数加权降维引起的光谱损失

采用PCA方法对损失的光谱进行降维

补偿因色度精度提升引起的光谱损失

有效提高降维的光谱精度。最后根据应用精度要求用前两步获得的主成分组合形成降维后数据。实验结果显示

提出方法的平均光谱精度为0.013 9

平均色度精度为0.705 8

色差稳定性为1.950 6

比现有的线性变换PCA法和LabPQR法分别提高了14%

15%;47%

68%和82%

表明新方法在光照变换色差稳定性、光谱精度及色度精度三方面均优于现有其他算法。

Abstract

To solve the problem brought by high dimensionality of multi-spectral images during color reproduction

a nonlinear dimensionality reduction method for multi-spectral images was presented. Firstly

according to the characteristics of human visual system

the CIE standard observer color matching functions were weighted to the source spectral reflectance and a Principal Component Analysis (PCA) method was used to the weighted spectrum to effectively improve the colorimetric precision and color difference stability of dimensionality reduction. Then

for the spectral reflectance loss caused by weighting color matching functions

a PCA method was imposed on the lost spectrum to compensate the lost spectral accuracy caused by the improvement of colorimetric precision to effectively improve the spectral precision of dimensionality reduction. Finally the principal components obtained from the first two steps were combined to form the low-dimensional spectral data. Experiments show that the proposed method can offer the average spectral precision in 0.013 9

average colorimetric precision in 0.705 8

and the color difference stability in 1.950 6

which is increased by 14% and 15%

47% and 68%

as well 84% and 82% as comparied those of the PCA and LabPQR methods. The method outperforms the existing methods in the colorimetric accuracy

spectral accuracy and color difference stability under different illuminants.

关键词

Keywords

references

ZHAO Y H, BERNS S R, TAPLIN A L, et al.. An investigation of multispectral imaging for the mapping pigments in paintings . Proc. of SPIE-IS&T Electronic Imaging, 2008,6810:681007-1-9.[2] BOCKHKO 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] WILLIAM J C, XIN Q, FORAN D J. Moving beyond color:the case for multispectral imaging for brightfield pathology . Proc. of IEEE International Symposium on Biomedical Imaging, ISBI09, 2009:1111-1114.[4] WU Q, ZENG L, ZHENG H, et al.. Precise segmentation of white blood cells by using multi spectral imaging analysis techniques . Proc. of Intelligent Networks and Intelligent Systems, Wuhan: ICINIS08, 2008:491-494.[5] WU C Y, LEE S M, WEN C H, et al.. Multi-spectral image acquisition system for color spectrum reproduction . Proc. of CVGIP,2003:115-122.[6] BAKKE M A, FARUP I, HARDEBERG Y J. Multispectral gamut mapping and visualizationa first attempt[J]. SPIE, 2005,5667:193-200.[7] 唐红, 郑文斌, 李宪霞. 主成分分析在光全散射特征波长选择中的应用[J]. 光学精密工程,2010,18(8):169-1698. TANG H, ZHENG W B, LI X X. Application of principal component analysis to selection of characteristic wavelengths with total light scattering[J]. Opt. Precision Eng., 2010,18(8):169-1698.(in Chineses)[8] DERKHA W M , ROSEN R M. Spectral colorimetry using LabPQR: An interim connection space[J]. Journal of IS&T, 2006,50(1):53-63.[9] ROSEN R M, DERHAK W M. Spectral gamuts and spectral gamut mapping[J]. SPIE-IS&T, 2006,6062:60620K-1-11.[10] TSUTSUMI S, ROSEN R M, BERNS S R. Spectral color management using interim connection space based on spectral decomposition[J]. Color Research & Application, 2008,33(4):282-299.[11] 赵全友, 潘保昌, 郑胜林. 复杂光照下的两步法颜色恒常性算法[J]. 光学精密工程,2009,17(4):859-866. ZHAO Q Y, PAN B CH, ZHENG SH L.Color constancy enhancement in two steps under variable illumination[J].Opt. Precision Eng.,2009,17(4):859-866.(in Chinese)[12] JOLLIFFE I T. Principal Component Analysis[M]. Springer-Verlag, New York, 1986:1.[13] 汤顺清. 色度学[M]. 北京: 北京理工大学出版社, 1991:69-76,95-100. TANG S Q. Colorimetry[M]. Beijing: Beijing Institute of Technology Press, 1991:69-76,95-100.(in Chinese)[14] IMAI H F, ROSEN R M, BERNS S R. Comparative study of metrics for spectral match quality . Proc. CGIV,2002:492-496.

浏览量

790

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Soft均值滤波的鲁棒主成分分析算法

航拍多光谱田间秸秆覆盖量反演模型的建立与优化

光谱色差与主分量特征融合的石窟表面风化智能评估

尖锐特征曲面散乱点云法向估计

用于静脉增强显示的图像融合算法