Classification of Rice Grains Using Morphological Features and ANN

Rice is one of the most important cereal grain crops. It is widely consumed throughout India. There is the growing concern for food security, with particular focus on rice being a staple food. Rice grain classification comes under Agro-Engineering study, which is very important research problem with respect to yield of rice grains as rice is one of the important food grains in Chhattisgarh region. The quality of rice affects the yield of rice. The recent advances in hardware and software have enabled the machine vision and imaging systems to detect, process, analyze, and display a wide range of finer details of objects from their digital images in real-time situations. Thus, grain grading and identification systems based on machine vision techniques are becoming potentially viable. The present research work deals with an approach to perform texture, morphological and colour based retrieval on a corpus of rice grain images. The work has been carried out using Image Warping and Pattern classification approach. The method has been employed to normalize food grain images and hence eliminating the effects of orientation using image warping technique with proper scaling.