<![CDATA[This study addresses the critical need for accurate and efficient tomato ripeness classification in agriculture and agribusiness, aiming to overcome the limitations of subjective manual methods. Leveraging advances in Computer Vision, this study implements a Data-efficient Image Transformer (DeiT) model for automatic classification of digital tomato images. DeiT, a Transformer-based architecture developed by Facebook AI Research, was chosen for its superior performance on small to medium-sized datasets, leveraging knowledge distillation. The model was trained using the Kaggle dataset, instrumented to enhance visual diversity, to classify tomatoes into “ripe” and “unripe” categories. Evaluation was performed using standard classification metrics including accuracy, F1-Score, and confusion matrix. The model demonstrated high performance, achieving an overall accuracy of 0.96 on the test dataset.]]>
Copyrights © 2025
