Non-destructive image processing based system for assessment of rice quality and defects for classification according to inferred commercial value

Abstract

Rice is among the three most consumed grains in the world, which makes its quality assessment an important task. Conventional methods based on manual inspection need specialized manpower, are time-consuming, error-prone, and at times, destructive. This paper presents an automatic, real-time and cost-effective image processing based system for classification of rice grains into various categories according to their inferred commercial value. The mechanism involves automatic segmentation of rice grains from background of image for discriminative feature extraction. Geometrical features are extracted in spatial domain, which aptly model the appearance characteristics of the grains. The feature sets are fed to an SVM (support vector machine) for multiple-class classification. The experimental results obtained using the proposed method indicate that the selected features have discriminatory properties for categorization of grain samples into different classes. Further milling defect grades are allotted to the samples based on proportion of broken kernels present in them proving a comprehensive grading of the quality of rice.