KEYWORDS: Cameras, Reflectivity, Digital cameras, Optical filters, Principal component analysis, Statistical analysis, Image classification, Multispectral imaging, Color difference, Digital imaging
Traditionally, the grade discrimination and classifying of bowlders (emeralds) are implemented by using methods based on people's experiences. In our previous works, a method based on NCS(Natural Color System) color system and sRGB color space conversion is employed for a coarse grade classification of emeralds. However, it is well known that the color match of two colors is not a true "match" unless their spectra are the same. Because metameric colors can not be differentiated by a three channel(RGB) camera, a multispectral camera(MSC) is used as image capturing device in this paper. It consists of a trichromatic digital camera and a set of wide-band filters. The spectra are obtained by measuring a series of natural bowlders(emeralds) samples. Principal component analysis(PCA) method is employed to get some spectral eigenvectors. During the fine classification, the color difference and RMS of spectrum difference between estimated and original spectra are used as criterion. It has been shown that 6 eigenvectors are enough to reconstruct reflection spectra of the testing samples.
For the training of the BP neural networks in CRT color conversion, some papers suggest using a uniformly distributed RGB training set model (URGB). However, this URGB model is single-directional. Therefore, when the number of the samples in a training set is under a certain amount, such as less than 51 2 (8 X 8 X 8), a URGB model may cause big prediction errors, especially in the backward conversion (XYZ to RGB). In this paper, we propose an improved training set model, with which a smaller training set can be drawn from a virtual URGB set. Our experimental results show that, an improved training set model can achieve a desired prediction accuracy in the whole CRT color space, even if the samples number in a training set is less than 512(8 X 8 X 8).
KEYWORDS: CRTs, Neural networks, RGB color model, Color reproduction, Data conversion, Colorimetry, Color vision, Color difference, Computing systems, Engineering education
As new method of characterizing CRT monitors is proposed. The features of this method are, it can take account of some color appearance factors, such as the appearance difference between self-luminous and surface color, but without the complexity of using any color appearance model, and it may improve the performances of an interpolation operation when an arbitrary assigned color is to be displayed on a CRT screen. The method is introduced more detailedly in Section 2, and preliminary experimental results are given in Section 3.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.