Abstract: Today, the challenges in agriculture are so big and complicated that agricultural professionals can't just look at them and figure them out. This study looks at the newest deep learning and computer vision techniques for finding and sorting mango leaf diseases. Leaf diseases cut the quality and quantity of mango crops by 30–80%, which costs the worldwide mango industry billions of dollars. We meticulously examine numerous scholarly articles on deep neural networks and image processing. We categorize current methodologies into three technical generations: conventional image processing systems, first deep learning applications, and advanced hybrid architectures that incorporate transfer learning, attention mechanisms, and explainable AI. We systematically assess performance metrics, dataset characteristics, and implementation challenges across diverse geographical regions. Our comprehensive evaluation framework and prospective research trajectories underscore sustainable, scalable, and farmer-centric solutions. This review is a complete guide for researchers studying tropical fruit and people who make agricultural technologies. This study fills in the gaps in research on dataset standardization, model interpretability, real-time deployment, and the integration of precision agriculture systems.
Keywords: Smart Farming, Deep Learning, Mango Diseases, Computer Vision, Precision Agriculture, Transfer Learning.
Title: Deep Learning for Early Disease Identification in Leaves: A Pathway to Sustainable Mango Production
Author: Shivam Saini, Rohit Goyal, Rakesh Arya
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Vol. 14, Issue 4, October 2026 - December 2026
Page No: 8-13
Research Publish Journals
Website: www.researchpublish.com
Published Date: 05-October-2026
