The Development of Color Quantitative System of Farm Product Based on the Chromaticity Theory

According to the chromaticity theory, the computer vision system used in color quantitative measurement was developed, which was marked by the 1980A color luminance meter. Munsell color system is selected to establish the mutual conversion between RGB and L*a*b* color model for camera, the conversion relation between RGB color space of CCD camera and L*a*b* color space under a big color gamut was expressed by the four-layer BP network, the same color card was measured synchronously by the color luminance meter and CCD camera, the color picture captured from CCD camera was expressed for RGB value as the input of neural network, XYZ value was gotten from the color luminance meter, and the L*a*b* value converted from XYZ value was regarded as the real color value of target card, namely the output of neural network. The method combining second general revolving combination design with genetic algorithm was put forward as the optimization for the hidden-layer structure of neural network. Using the data of testing set to test this network and calculating the color difference between forecast value and true value, the result showed than the maximum color difference was 5.6357 NBS, the minimum color difference was 0.5311 NBS, and the average color difference was 3.1744 NBS.