Identification Texture of Rice Varieties by Feature Extraction using GLCM

Abstract

Rice is one of the components of staple ingredients included in the issue of world food security in the Sustainable Development Goals (SDGs) program. A large number of varieties of rice types allows deviations in the field by mixing good rice varieties with other varieties to increase profits. This problem causes consumers to experience economic losses; on the other hand, distinguishing rice varieties is difficult to do directly only through eyesight. This study tries to make an initial approach to get the similarity value of each rice-type texture. This study discusses the extraction of texture features in 3 rice varieties, including organic rice, Mentik Wangi, Rojo Lele, and Basmati India. The feature extraction method used is the Gray Level Co-occurrence Matrix (GLCM) for assessing the texture of an image variety of rice and evaluated with PSNR and MAE.