Rice variety identification using artificial neural network

Rice is considered staple food as it is eaten in large quantity in all over world. And it serves as a crucial source of energy and nutrition. With the diverse array of rice varieties cultivated globally, the need for accurate and efficient identification methods becomes paramount. As all rice varieties are not equally valuable unscrupulous persons become tempted to mix up lower cost variety in costly one. Physical attributes of rice like size, shape, cooking characteristics etc. offer lot of avenues for identification of such practices. Among physical attributes is image analysis. This study was conducted with objective of using image analysis using artificial neural network to identify Basmati and Gujarat 17 verities. It was found in this study that rice variety identification is quite feasible using simple feed forward neural network particularly for those verities which differ in visual parameters i.e. like Basmati and Gujarat 17 used in this study.