Automated Plant Disease Detection Using CNNs and YOLOv5: A Comprehensive Approach with Grad-CAM and VGG16

Convolutional neural networks will be used in the proposed research project to create a plant disease detection system (CNNs). Object detection is used (Yolov5), so it is the model having (Gradcam and yolov5 with vgg16). The system will be created to analyze digital photos and quickly and effectively detect diseases in plant leaves. With the help of a sizable collection of plant photos, both healthy and diseased plants will be included, and the CNN model will be trained to recognize different diseases. The study will go through various phases, including data gathering, data preprocessing, model construction, and model assessment. To eliminate artifacts and to standardize the photos, the acquired data will be preprocessed. Modern methods will be used in the design of the CNN model, which will then be optimized to attain high disease detection accuracy. By offering an automated and precise technique for identifying plant diseases, the suggested technology has the potential to revolutionize the field of plant disease detection. This may result in prompt treatment and intervention, reducing crop loss and increasing agricultural output. The proposed approach can also decrease the need for manual diagnosis and inspection, saving farmers and researchers time and money on labor. The overall goal of this research project is to support the creation of an effective and trustworthy system for detecting plant diseases that can have a significant impact on the agriculture sector.