• SATYAM TIWARI
• SANDEEP KUMAR VISHWAKARMA
• ER. SHIVAM AWASTHI

Plant diseases are a major food safety nuisance. The biggest challenge in agriculture is to detect plant diseases. State-of-the-art convolutional neural networks (CNNs) provide excellent results for solving computer vision image classification tasks. Transfer learning allows you to build deep CNN networks in the most cost-effective way. In this work, we developed a CNN model based on transfer learning to accurately identify plant diseases. The dataset used consists of 54,306 images containing leaves from 38 different plant classes. As a pre-trained model for transfer learning, we focused primarily on the popular CNN architecture, the ResNet 50 network. In addition, we tried several transfer learning architectures using other popular pre-trained models (VGG16, VGG19, AlexNet) and compared them to the proposed model. The proposed model showed the best performance with a training accuracy of 98.47%.

"AGRICULTURE DISEASE DETECTION USING RESNET50 AND NEURAL NET CLASSIFIER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.a335-a340, May-2022, Available :http://www.jetir.org/papers/JETIR2205042.pdf

"AGRICULTURE DISEASE DETECTION USING RESNET50 AND NEURAL NET CLASSIFIER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppa335-a340, May-2022, Available at : http://www.jetir.org/papers/JETIR2205042.pdf