• Vaijayanta Yadav
• Dr. Minakshi M Sonawane

The accurate identification of plant leaf illness crucial for improving agricultural production and ensuring food security. Traditional disease detection strategies require manual inspection, which takes a great deal of time, is liable to human error and requires specialized knowledge. With advancements in machine learning (ML), automated disease detection has emerged as a reliable and efficient alternative. This study explores the using ML techniques as a Random Forests, Support Vector Machines, and Image-recognition neural architecture to automatic recognition as well as categorization of plant leaf condition through image analysis. The major impact that plant diseases have on agricultural productivity, the necessity for a precise and user-friendly detection system, and the limitations that currently exist manual methods led to the selection of this study topic. The proposed system integrates both online and offline functionalities, ensuring accessibility for farmers in areas with limited internet connectivity. Experimental results demonstrate that CNN-based models achieve the highest accuracy, outperforming traditional methods in both detection speed and precision. By providing a scalable, real-time, and automated disease detection system, this study contributes to early intervention strategies, helping farmers and agricultural experts improve crop health and productivity.

Identification, Plant leaf diseases, Agricultural, Image Analysis,CNN,SVM.

"Plant Leaf Disease Identification Using Machine Learning Methods ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 8, page no.186-194, August-2025, Available :http://www.jetir.org/papers/JETIRHA06026.pdf

"Plant Leaf Disease Identification Using Machine Learning Methods ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 8, page no. pp186-194, August-2025, Available at : http://www.jetir.org/papers/JETIRHA06026.pdf