Abstract: Yellow-colored rice in mass rice is detected by manual method presently, therefore it is difficult that the method is executed effectively and accurately in market business. A rice quality evaluation system was developed. Making use of image recognition technology, a study was made on the feasibility of distinguishing objectively yellow-colored rice from mass rice according to the RGB color theory. An optimal chromatic value was obtained based upon a lot of experiments on the distribution of the chromatic value. It is revealed that automatic detection of yellow-colored rice using image-processing technology could be an effective way for discerning and calculating the number and percentage of yellow-colored rice kernel.