Development of an integrated variety and appearance quality measurement system for milled rice

The need has arisen in China for a comprehensive approach to get the variety and appearance quality of milled rice accurately. In this study, near-infrared spectroscopy has been used to get variety of milled rice. A machine vision system has been established to get five appearance quality parameters (length-width ratio, chalky rice rate, broken rice rate, yellow-colored rice rate, and fissured rice rate) of milled rice. Thus, an integrated variety and appearance quality measurement system for milled rice has been developed. Based on the integrated system, the possibility of variety classification using the machine vision is investigated, and a new variety classification method based on near-infrared spectroscopy and machine vision is proposed. The performance of the new method is verified compared to conventional variety classification method, which shows that the classification accuracy can be improved by combining the near-infrared spectroscopy and the machine vision.