Rice seed image classiﬁcation based on HOG descriptor with missing values imputation
Huy Nguyen-Quoc, Vinh Truong Hoang
Rice is a primary source of food consumed by almost half of world population. Rice quality mainly depends on the purity of the rice seed. In order to ensure the purity of rice variety, the recognition process is an essential stage. In this paper, we ﬁrstly propose to use histogram of oriented gradient (HOG) descriptor to characterize rice seed images. Since the size of image is totally random and the features extracted by HOG can not be used directly by classiﬁer due to the different dimensions. We apply several imputation methods to ﬁll the missing data for HOG descriptor. The experiment is applied on the VNRICE benchmark dataset to evaluate the proposed approach.
HOG descriptor; KNN imputation; linear interpolation; missing value imputation; rice seed image classiﬁcation; zero imputation;