Plant Leaves Disease Detection and Classification: Insights from Machine Learning and Deep Learning Approaches - A Review

Grace Thabitha J., Dr. Ponnusamy R.

Abstract: Plant diseases pose a significant problem globally, greatly impacting crop quality and yield. This, in turn, affects global food security. Catching plant leaf diseases early and accurately is crucial for effective disease management strategies. Lately, machine learning (ML) and deep learning (DL) techniques have shown great promise in automating and improving the detection of plant diseases. This paper aims to provide a thorough review of current research on detecting and classifying plant leaf diseases using ML and DL algorithms. We begin by discussing the importance of early disease detection and the challenges linked with traditional methods. Then, we look into the key challenges and needs of plant disease detection systems. We also dive into existing studies that utilize ML and DL approaches for identifying plant leaf diseases. Additionally, we explore the evaluation methods, performance metrics, and datasets used to measure the effectiveness of these techniques. On top of that, we highlight emerging trends and recent advancements in this domain, such as image augmentation methods, transfer learning, and ensemble algorithms.

Keywords: Plant disease, Leaf disease, Machine Learning, Deep Learning, Computer Vision

How to Cite?: Grace Thabitha J., Dr. Ponnusamy R., "Plant Leaves Disease Detection and Classification: Insights from Machine Learning and Deep Learning Approaches - A Review", Volume 14 Issue 1, January 2025, International Journal of Science and Research (IJSR), Pages: 102-108, https://www.ijsr.net/getabstract.php?paperid=SR241230211809, DOI: https://dx.doi.org/10.21275/SR241230211809

Download Citation: APA | MLA | BibTeX | EndNote | RefMan