• Shubhada Ekanath Tamhanekar
• S.B.Kadam
• Shravani Shivram Mhaskar
• Nimat Mehboob Shaikh

Abstract—The world’s food supply is greatly dependent on plants. Plant diseases are caused by a variety of environmental variables, which cause large losses in productivity. Plant disease identification by hand, however, is a laborious and prone to error procedure. It may not always be an accurate way to recognize plant diseases and stop them from spreading. By making early plant disease detection possible, the adoption of cutting-edge technologies like machine learning (ML) and deep learning (DL) can aid in overcoming these obstacles. The most current developments in the application of ML and DL methods for plant disease identification are examined. The study’s studies show how these strategies can be used to increase the precision and productivity of plant disease detection, and the research is centered on publications from 2015 to 2022. This paper also discusses the difficulties and restrictions involved in applying ML and DL for the identification of plant diseases, including problems with data accessibility, imaging quality, and the capacity to distinguish between healthy and diseased plants. This paper presents a comprehensive approach to plant disease detection and gives remedies using deep learning methodologies, focusing on the utilization of VGG19 and ResNet architectures for feature extraction and classification. The proposed system involves several key components: preprocessing of input images, feature extraction through pre-trained CNN models, selection of appropriate activation functions for classification, and performance evaluation metrics to assess the model’s effectiveness.A user-friendly plant disease detection system that can examine leaf photos and classify them according to the particular illness present is the desired outcome.The proposed system is able to detect the disease of plant with cnn model vgg19 and resnet-9 with accuracy 86.42 % and 94.86 % respectively.

Deep learning ,VGG19, Resnet, Activation function, plant disease detection, image processing ,convolutional neural networks, performance evaluation,pytorch Framework

"Deep Leaf: A Comprehensive Analysis of Deep Learning Technique CNN For plant Diseases Diagnosis and Remedies", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.i37-i44, March-2024, Available :http://www.jetir.org/papers/JETIR2403806.pdf

"Deep Leaf: A Comprehensive Analysis of Deep Learning Technique CNN For plant Diseases Diagnosis and Remedies", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppi37-i44, March-2024, Available at : http://www.jetir.org/papers/JETIR2403806.pdf