Researches and Application of Algorithm on Core Characteristic Extraction for Auto-separating System of Watermelon Seeds

The algorithm of extracting a series of characteristic value, taking watermelon seeds as the research object, has been successfully applied into the software system of separating watermelon seeds automatically. By extracting characteristic values, like the length of orthogonal long and minor axis of the watermelon seeds, the proportion between the length and width, the area, the degree of connecting superficial pattern, the coverage degree of black region and the distribution difference of histogram gradation and screening the watermelon seeds, the software system finally divides and picks the qualified melon seeds. The system takes visual interface. It has the interactive function between man and machine, being more objective, more accurate and more convenient, compared with the hands´ works. The realization of real-time image gathering function enormously enhances the speed and the efficiency. The core technology of the software system also can be served as important reference for other relevant fields.