Title: Automatic Cantaloupe Fruit Classification Using Deep Convolutional Neural Networks
Authors: Beesan M. Alaydi , Heba W. Zourob, Samy S. Abu-Naser
Volume: 10
Issue: 2
Pages: 13-18
Publication Date: 2026/02/28
Abstract:
Automatic classification of agricultural products plays a vital role in improving crop quality assessment and supporting intelligent farming systems. With recent advances in deep learning, convolutional neural networks (CNNs) have demonstrated strong performance in image-based classification tasks . In this study, an automatic system for cantaloupe fruit classification is proposed using a deep convolutional neural network based on the pre-trained VGG16 architecture. A dataset of cantaloupe images was collected and divided into training, validation, and testing sets. Image preprocessing techniques, including resizing, normalization, and data augmentation, were applied to enhance model generalization. The proposed model was trained using a binary classification framework with a sigmoid activation function and evaluated using classification accuracy and confusion matrix analysis. Experimental results show that the proposed model is capable of learning discriminative visual features of cantaloupe fruits and achieved an overall classification accuracy of 51.9% on the test dataset. These findings demonstrate the potential of deep learning-based approaches for automated fruit quality assessment in smart agriculture applications.