Plant Disease Detection and Classification Using Deep Learning Techniques

The early and accurate detection of plant diseases is very important in protecting crop yield and ensuring food security.This thesis is going to explore how deep learning methods, especially Convolutional Neural Networks (CNNs) and ResNet-50, can help identify and classify diseases in Tomato, Potato, and Pepper plants.A dataset of over 38,000 images of both healthy and diseased leaf samples were collected.Different data augmentation techniques like rotation, shearing, zooming, and flipping were used to increase the efficiency of models and balance the number of images in each class.This research looks at how well a custom CNN and a fine-tuned ResNet-50 model perform on the three crops by checking their training, validation, and test results.The result shows that the CNN model's performance was reasonably well, and it achieved test accuracy of 94.12% (Tomato), 92.83% (Potato), and 91.98% (Pepper), while the ResNet-50 model has shown much better results, with an accuracy score of 99.37% and has shown a strong performance across all datasets.Diseases like Late Blight and Yellow Leaf Curl Virus, that are very difficult to visually distinguish but ResNet-50 was very precise at identifying these diseases.This work shows how deep learning is very effective in plant disease detection but also explores that these models could be used in real farming environments to help farmers take quick action and reduce crop losses.By decreasing dependence on manual inspection and helping in early disease detection, the research helps to support greener, technology-driven agriculture.