A COMPARATIVE STUDY OF ADVANCED DEEP LEARNING FOR AUTOMATED ORANGE FRUIT DISEASES CLASSIFICATION

The diseases affecting orange fruits are one of the major challenges to citrus farming around the worldwide. Conventional techniques for detecting these diseases are laborious, time-consuming and may result in erroneous outcomes. This study proposes an advanced deep learning approach to enable fast and accurate classification of various orange fruit diseases through images. This work utilizes transfer learning and involves tuning three pre-trained Convolutional Neural Network (CNN) models: Inception-V3, Inception-ResNet-V2, and EfficientNet-V2-B3 on a large dataset of orange fruit images. The proposed approach is tested for five values of dropout percentages (10% to 50%), accompanied by extensive data augmentation strategies to improve generalization capabilities. The performance of machine learning models is assessed by evaluating parameters such as accuracy rate, precision, recall value, and confusion matrix. The effectiveness of deep learning is shown through high classification: The EfficientNet-V2-B3 achieved the highest accuracy of 99.1% with a loss of 0.055 at a 30% dropout rate. Meanwhile, Inception-ResNet-V2 attained 96.7% accuracy, and Inception-V3 reached 96.5% accuracy. These outcomes significantly outperform classical approaches. This study offers a strong and scalable approach to detecting various diseases at an early stage to encourage sustainable citrus growth and reduce economic challenges associated with farming. A web application was also developed based on the best-model approach for easy activation of AI in farming.