A Review on Tomato Quality Classification Using Transfer Learning and Machine Learning Classifiers

Tomato quality classification plays an important role in modern agriculture, influencing both market value and supply chain efficiency. Manual sorting methods are often unreliable and impractical for large-scale processing. Recent advances in computer vision and artificial intelligence have led to the development of automated classification systems. This review investigates hybrid approaches that combine deep feature extraction using transfer learning models with traditional classifiers such as SVM, decision trees, and instance-based learners. The paper summarizes recent techniques used for tomato ripeness and quality grading, analyzing the datasets, model performance, architectural improvements, and deployment challenges. It further highlights potential directions to enhance scalability, efficiency, and practical implementation in agricultural environments.