Class-based spectral reconstruction based on unmixing of low-resolution spectral information

This paper proposes a class-based spectral estimation method for high-resolution red, green, and blue (RGB) images and corresponding low-resolution spectral data. Each spectrum in the low-resolution data is assumed to be a mixture of spectra of different classes. Then, the spectral estimation matrix for every class is derived using a regression approach, in which the clustering results of the high-resolution RGB image are used to incorporate spectral unmixing. Experiments confirm reduced normalized root mean squared error for the spectral images if the number of classes in the clustering is appropriately selected. In addition, the experimental results show that the spectra are accurately reconstructed even when they are observed as mixed spectra in the low-resolution data.

[1]  Hans Brettel,et al.  Multispectral color image capture using a liquid crystal tunable filter , 2002 .

[2]  Hideaki Haneishi,et al.  Beyond Red-Green-Blue (RGB) : Spectrum-Based Color Imaging Technology , 2008 .

[3]  Masahiro Yamaguchi,et al.  Maximum a posteriori estimation of spectral reflectance from color image and multipoint spectral measurements. , 2007, Applied optics.

[4]  Xiandou Zhang,et al.  Reconstructing spectral reflectance by dividing spectral space and extending the principal components in principal component analysis. , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  Oili Kohonen.  Multiresolution-Based Pansharpening in Spectral Color Images , 2010, CGIV/MCS.

[6]  Ville Heikkinen,et al.  Regularized learning framework in the estimation of reflectance spectra from camera responses. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[7]  Liang Gao,et al.  Snapshot Image Mapping Spectrometer (IMS) with high sampling density for hyperspectral microscopy , 2010, Optics express.

[8]  Hui-Liang Shen,et al.  Reflectance reconstruction for multispectral imaging by adaptive Wiener estimation. , 2007, Optics express.

[9]  Amir Averbuch,et al.  Spectral multiplexing method for digital snapshot spectral imaging. , 2009, Applied optics.

[10]  Masahiro Yamaguchi,et al.  Natural color reproduction in the television system for telemedicime , 1997, Medical Imaging.

[11]  Dieter Oertel,et al.  Unmixing-based multisensor multiresolution image fusion , 1999, IEEE Trans. Geosci. Remote. Sens..

[12]  Brian A Wandell,et al.  Spectral estimation theory: beyond linear but before Bayesian. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  Michael E. Schaepman,et al.  Unmixing-Based Landsat TM and MERIS FR Data Fusion , 2008, IEEE Geoscience and Remote Sensing Letters.

[14]  Robert A. Schowengerdt,et al.  Synthesis of imagery with high spatial and spectral resolution from multiple image sources , 1994 .

[15]  Audrey Minghelli-Roman,et al.  Spatial resolution improvement of MeRIS images by fusion with TM images , 2001, IEEE Trans. Geosci. Remote. Sens..

[16]  Toshio Uchiyama,et al.  Color image reproduction based on multispectral and multiprimary imaging: experimental evaluation , 2001, IS&T/SPIE Electronic Imaging.

[17]  M E Gehm,et al.  Single-shot compressive spectral imaging with a dual-disperser architecture. , 2007, Optics express.

[18]  T. Obi,et al.  Nonlinear estimation of spectral reflectance based on Gaussian mixture distribution for color image reproduction. , 2002, Applied optics.

[19]  Masahiro Yamaguchi,et al.  Piecewise Wiener estimation for reconstruction of spectral reflectance image by multipoint spectral measurements. , 2009, Applied optics.

[20]  J. Parkkinen,et al.  Spectral vision system for measuring color images , 1999 .

[21]  Masahiro Yamaguchi,et al.  Comparison of spectral image reconstruction methods using multipoint spectral measurements , 2008, CGIV/MCS.

[22]  Russell C. Hardie,et al.  Application of the stochastic mixing model to hyperspectral resolution enhancement , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[23]  B R Hunt,et al.  Training of a neural network for image superresolution based on a nonlinear interpolative vector quantizer. , 2000, Applied optics.

[24]  H Haneishi,et al.  System design for accurately estimating the spectral reflectance of art paintings. , 2000, Applied optics.

[25]  D. Dupont.  Study of the reconstruction of reflectance curves based on tristimulus values: Comparison of methods of optimization , 2002 .

[26]  J. C. Price,et al.  Combining panchromatic and multispectral imagery dual resolution satellite instruments , 1987 .

[27]  Miguel Vélez-Reyes,et al.  A comparison of unmixing algorithms for hyperspectral imagery , 2009, Defense + Commercial Sensing.

[28]  Peter Morovic,et al.  Metamer-set-based approach to estimating surface reflectance from camera RGB. , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

[29]  A. I. Negueruela,et al.  Use of three tristimulus values from surface reflectance spectra to calculate the principal components for reconstructing these spectra by using only three eigenvectors. , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

[30]  Peter D. Burns,et al.  Analysis Multispectral Image Capture , 1996, CIC.

[31]  Russell C. Hardie,et al.  Hyperspectral resolution enhancement using high-resolution multispectral imagery with arbitrary response functions , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Bernhard Hill.  Color capture, color management, and the problem of metamerism: does multispectral imaging offer the solution? , 1999, Electronic Imaging.

[33]  Toshio Uchiyama,et al.  Development of a 16-band multispectral image archiving system , 2005, IS&T/SPIE Electronic Imaging.