Enhancing rice seed purity recognition accuracy based on optimal feature selection

This study proposes a robust and accurate approach for classifying rice variety purity to meet stringent agricultural standards. To achieve this, we construct a comprehensive dataset by leveraging diverse types of features encompassing morphological properties, overall image structure, texture information, and color distribution from rice seeds. Subsequently, we employ advanced feature selection techniques, including filter methods (Correlation, Chi-square, ANOVA), wrapper methods (Recursive Feature Elimination — RFE), and embedded methods (Random Forest, Decision Trees), to identify the most significant features. Through rigorous experimentation with eight machine learning algorithms, we find that using Random Forest for feature selection, in combination with the SVM classifier, yields the best performance. Specifically, Random Forest reduces the feature set by more than half, from 172 to 80, remarkably enhancing classification accuracy from 94.73% to 96.11%. This paper highlights the potential of the proposed method to offer a robust and efficient solution for rice seed purity identification in agricultural applications, while also opening up new horizons for similar studies. • Proposes a robust method for classifying rice variety purity with high accuracy. • Combines feature selection and ML methods to enhance model effectiveness. • Employs a diverse dataset of morphological, texture, and color features to capture rice seed complexity. • Applies feature selection to find key features, boosting accuracy and interpretability. • Removes over half of the insignificant features, improving accuracy to 96.11%.