Determination of Effective and Specific Physical Features of Rice Varieties by Computer Vision In Exterior Quality Inspection

Authors : İlkay ÇINAR, Murat KÖKLÜ

Pages : 229-243

View : 103 | Download : 84

Publication Date : 2021-12-25

Article Type : Research Paper

Abstract :In this study, feature extraction processes were performed based on the image processing techniques using morphological, shape and color features for five different rice varieties of the same brand. A total of 75 thousand pieces of rice grain were obtained, including 15 thousand pieces of each variety of rice. Preprocessing operations were applied to the images and made available for feature extraction. A total of 106 features were inferred from the images; 12 morphological features and 4 shape features obtained using morphological features and 90 color features obtained from five different color spaces insert ignore into journalissuearticles values(RGB, HSV, L*a*b*, YCbCr, XYZ);. In addition, for the 106 features obtained, features were selected by ANOVA, X2 and Gain Ratio tests and useful features were determined. In all tests, out of 106 features, the 5 most effective and specific features were obtained roundness, compactness, shape factor 3, aspect ratio and eccentricity. The color features were listed in different order following these features.
Keywords : Color spaces, Feature extraction, Feature selection, Image processing, Quality control