An Effective Review on Classification and Detection of Fruit Leaf Diseases using Machine Learning and Deep Learning Techniques

Joice Shakila A., Dr. Saravanan S.

Abstract: The effective detection of leaf diseases in fruit crops is vital for optimizing agricultural productivity and mitigating economic losses. Recent advancements in Machine learning (ML) and Deep learning (DL) have revolutionized the field of plant pathology, offering innovative solutions for accurate and efficient disease detection. This review paper provides a comprehensive overview of ML and DL techniques applied for classifying and detecting fruit leaf diseases. We systematically evaluate various methods, including classical ML algorithms like Support Vector Machines and Random Forests, and state - of - the - art DL models such as Convolutional Neural Networks, Recurrent Neural Networks, and Transfer Learning. The paper highlights key factors influencing model performance, such as dataset quality, Image Resolution, Pre - processing methods, and Feature Extraction techniques. We also explore the challenges and limitations associated with these technologies, including the need for large annotated datasets, computational demands, and deployment in real - world agricultural settings. By synthesizing current research trends and technological advancements, this review aims to provide a clear understanding of the capabilities and limitations of ML and DL approaches for leaf disease detection and classification to propose directions for future research and development in this field.

Keywords: Machine Learning, Deep Learning, Fruit diseases, Convolutional Neural Networks, Transfer Learning

How to Cite?: Joice Shakila A., Dr. Saravanan S., "An Effective Review on Classification and Detection of Fruit Leaf Diseases using Machine Learning and Deep Learning Techniques", Volume 14 Issue 1, January 2025, International Journal of Science and Research (IJSR), Pages: 1078-1084, https://www.ijsr.net/getabstract.php?paperid=SR25124223041, DOI: https://dx.doi.org/10.21275/SR25124223041