Title: Revolutionizing Lemon Quality Control: A Convolutional Neural Network Approach
Authors: Heba I. A. Alqedra, Samy S. Abu-Naser
Volume: 9
Issue: 6
Pages: 56-63
Publication Date: 2025/06/28
Abstract:
The classification of agricultural products, particularly lemons, based on quality is crucial for ensuring consumer safety, maintaining market value, and meeting the increasing demand for high-quality produce. In this study, we introduce an innovative solution that utilizes deep learning techniques, specifically Convolutional Neural Networks (CNNs), to automate lemon quality classification. The model was trained on a comprehensive dataset of 6,000 images, equally distributed between "good quality" and "bad quality" lemons. The results demonstrate an impressive 99.48% accuracy on the validation set, underscoring the effectiveness and efficiency of CNNs in image-based classification tasks within agriculture. This approach provides a scalable, cost-effective, and reliable alternative to traditional manual inspection methods. Furthermore, it offers significant potential for integration into automated quality control systems within the agricultural industry. However, challenges such as variability in image quality and lighting conditions may affect model performance, requiring further refinement. Future work will focus on addressing these challenges to enhance the robustness and applicability of the model.