| Smart Agriculture: Automated Detection and Classification of Fruit Diseases Using CNN-Based Image Processing |
| Paper ID : 1035-ICEEM2025 (R1) |
| Authors |
|
Tamer M. Nassef *1, Farah Hamdy Mouhebeldin1, Nada Ahmed Mahmoud1, Mohamed N. Saad2 1Faculty of Computer Science, October Modern University for Sciences and Arts (MSA) 2Biomedical Engineering Department, Faculty of Engineering, Minia University, Egypt |
| Abstract |
| This study investigates the integration of advanced agricultural technologies—specifically image preprocessing techniques and machine learning (ML) models—into the context of Egyptian agriculture. It aims to demonstrate how the adoption of these digital solutions can transform traditional farming practices by enhancing productivity, reducing operational costs, and improving the quality and consistency of agricultural produce. The research places significant emphasis on the critical role of image preprocessing in the data pipeline, as it directly influences the performance of machine learning models. By standardizing preprocessing methods and tailoring them to specific types of fruits, the models achieved improved feature extraction, more accurate defect detection, and higher classification accuracy. The study explores how these innovations can be adapted to meet the unique environmental and economic challenges faced by Egyptian agriculture, including climate variability, water scarcity, and limited financial resources. By designing flexible and context-aware ML systems, the research shows that it is possible to develop scalable solutions that are both efficient and sustainable. The findings suggest that targeted application of AI and image analysis can lead to more precise decision-making and higher crop yields. Ultimately, this work contributes to the growing field of smart agriculture by offering practical insights into how Egyptian farmers and producers can adopt technology to compete both locally and in international markets. |
| Keywords |
| CNN, Defect Detection, Fruit Diseases, Fruit Quality Assessment, Image processing |
| Status: Accepted |