Artificial Intelligence-Based Rice Variety Classification : A Comprehensive Review

Rice variety classification plays a crucial role in ensuring food quality, agricultural productivity, seed purity, and market value. Traditional classification methods rely heavily on expert knowledge and manual inspection, which are time-consuming, subjective, and prone to error. With the rapid advancement of artificial intelligence (AI), computer vision, and deep learning techniques, automated rice variety classification has gained significant research attention. Recent studies have explored convolutional neural networks, vision transformers, transfer learning, and ensemble learning models to improve classification accuracy using grain-level, leaf-level, and field-level images. These approaches leverage feature extraction, attention mechanisms, and data augmentation to handle intra-class similarity and inter-class variation among rice varieties. This review provides a systematic overview of state-of-the-art AI-based rice variety classification techniques, highlighting methodologies, datasets, advantages, and limitations reported in recent literature. Furthermore, it analyzes research findings, identifies key challenges such as dataset scarcity, environmental variability, and model generalization, and outlines future research directions. The study aims to serve as a comprehensive reference for researchers and practitioners seeking to develop robust, scalable, and interpretable rice variety classification systems using modern AI techniques.