1. 北京理工大学光电工程系颜色科学与工程国家专业实验室,北京 100081 2. Delft Center for Systems and Control, Delft University of Technology, 2628 CD Delft, the Netherlands
Study of Approaches to Spectral Reflectance Reconstruction Based on Digital Camera
YANG Ping1, LIAO Ning-fang1, SONG Hong2
1. National Laboratory of Color Science and Engineering, Department of Optical Engineering, Beijing Institute of Technology, Beijing 100081, China 2. Delft Center for Systems and Control, Delft University of Technology, 2628 CD Delft, the Netherlands
Abstract:It is still challenging to reconstruct the spectral reflectance of a surface using digital cameras under given luminance and observation conditions. A new approach to solving the problem which is based on neural network and basis vectors is proposed. At first, the spectral reflectance of the sample surface is measured by spectrometer and the response of an digital camera is recorded. Then the reflectance is represented as a linear combination of several basis vectors by singular value decomposition (SVD). After that, a neural network is trained so that it is able to approximate the relationship between the camera responses and the coefficients of basis vectors accurately. In the end, the spectral reflectance can be reconstructed based on the neural network and basis vectors.In the present paper, the authors reconstructed the spectrum reflectance based on neural network and basis vectors. Compared with other traditional methods, neural network expands the space of unknown function F(S) from linear functions to more general nonlinear functions, which gives more accurate estimation of the coefficients ak and better reflectance reconstruction. Results show that the reflectance of standard Munsell color patch (Matte)can be reconstructed successfully with mean of RMS which is 0.023 4. Compared with linear approximation method, reconstruction of standard Munsell color patch (Matte)using this approach reduces the reconstruction error by 67%. Since the neural network can be implemented by Matlab neural network toolbox, this method can be easily adopted in many other cases. Therefore we conclude that this approach has advantages of higher accuracy, easy implementation and adaptation, thus can be used in many applications.
杨萍1,廖宁放1,宋宏2 . 基于彩色数字相机的光谱反射率重建方法研究[J]. 光谱学与光谱分析, 2009, 29(05): 1176-1180.
YANG Ping1, LIAO Ning-fang1, SONG Hong2 . Study of Approaches to Spectral Reflectance Reconstruction Based on Digital Camera . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(05): 1176-1180.
[1] Hardeberg J Y. Acquisiuion and Reproduction of Colored Images: Colorimetric and Multispectral Approaches. France:Ecole Supe′rieurNationale des Tele′communications,1999. [2] Dupont D. Color Research & Application,2002,27(2):89. [3] Raimondo Schettini,Silvia Zuffi. Neural Computing and Applications,2007,16(1):69. [4] Demuth H, Beale M, Hagan M. Neural Network Toolbox 5 User’s Guide,The Math Works, Inc.,2007. [5] HE Yong, LI Xiao-li, SHAO Yong-ni(何 勇,李晓丽,邵咏妮). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(5): 850. [6] Johnson Tony. Displays, 1996, 16(4): 183. [7] Cheng Fang-Hsuan,Yang Chih-Yuan. Proc. SPIE, 2000, 4080: 167. [8] Yamaguchi Masahiro et al. Proc. SPIE, 2002, 4663: 15. [9] Berns R S. Challenges for Color Science in Multimedia Imaging. In Conference Proceedings, CIM’98, Derby, UK., Colour Imaging in Multimedia, 1998. 123. [10] Ohya Yuri, Obi Takashi, Yamaguchi Masahiro et al. Proc. SPIE, 1998, 3335: 263. [11] Ng Du-Yong,Allebach Jan P. Proc. SPIE, 2004, 5293: 38. [12] Alman David H, Ningfang Liao. Color Res. & Appl., 2002, 27(2): 122. [13] Barnard Kobus, Funt Brian. Color Res. & Appl., 2002, 27(3): 152. [14] Cheung Vien, Westland Stephen, Thomson Mitch. Color Res. & Appl., 2004, 29(6): 406.