MACHINE VISION COLOR CALIBRATION IN ASSESSING CORN KERNEL DAMAGE

The effectiveness of many color image analysis and classification meth odologies depends on the constancy of the scene illumination. In reali ty scene illumination often changes over time. In this article, we pre sent a simple, bur effective method for calibration to improve color i mage classification with changing illumination. Color changes due to c hanging illumination were captured using a gray reference plate. The e xtent of the color changes in each of the RGB channels was calculated based on art equation derived from the spectral reflectance model. The se values formed a transformation matrix which was used to transform t he image RGB values to compensate for the color changes. A set of expe riments for classifying the color of mold-damaged corn kernels was per formed to demonstrate the effectiveness of the color calibration metho d in the presence of changes in illumination.