A dataset of colour spectra can be represented as a linear combination of few principal spectra.The principal components of a spectral dataset are usually generated by the method of Principal Component Analysis (PCA). The Independent Component Analysis (ICA) has been used to abstract the independent components of the spectral dataset by some researchers in recent years and enables data compression. In this paper, the feature spectra of spectral reflectance of 50 cases Munsell colour cards and 50 cases birch leaves are abstracted by ICA separately. The reflectance of 150 cases Munsell colour cards and 150 cases birch leaves are reconstructed with the multi-spectral imaging and the algorithm of spectral reconstruction, and with three sets of filters, each compose of two, three, and four filters, and three to fifteen dimensions subspace. The reconstruction results are evaluated by the CIE1976 colour difference and the spectrum reconstruction errors. According to the results of reconstruction, the relationship between the subspace dimensions, the number of filters and the reconstruction colour differences, spectral error are analyzed in this paper.
展开▼