Rice being one of the most widely produced and consumed cereal crops in the world, is also the one of the main sustenance in our country because of its economical and nutritious nature. Rice, starting from farm to our table, goes through some manufacturing steps such as a cleaning process, color sorting and classification. If these stages are to be mentioned briefly, cleaning is the process of separating rice from foreign substances, classification is the process of separating broken ones with

more »

... turdy ones; color extraction is the process of separating the stained and striped ones except the whiteness on the rice surface. In this study, a computerized vision system was developed in order to distinguish between two proprietary rice species. A total of 3810 rice grain's images were taken for the two species, processed and feature inferences were made. 7 morphological features were obtained for each grain of rice. With these features, models were created using LR, MLP, SVM, DT, RF, NB and k-NN machine learning techniques and performance measurement values were obtained. Success rates in the classification were obtained 93.02% (LR), 92.86% (MLP), 92.83% (SVM), 92.49% (DT), 92.39% (RF), 91.71% (NB), 88.58% (k-NN). When we look at the results of the success rate of obtain, it is possible to say that the study achieved success.