Multi Stage Neural Network Based Ensemble Learning Approach for Wheat Leaf Disease Classification

This project aims to develop an automated deep learning-based classification system for wheat plant disease detection using the publicly available Wheat Plant Diseases dataset from Kaggle. The dataset includes images of various wheat diseases, which are critical to identify early to prevent crop damage and yield loss. The study evaluates and compares the performance of several state-of-the-art convolutional neural network (CNN) architectures, including ResNet50, InceptionNet, DenseNet201, VGG19, NASNetLarge, MobileNetV2, Vit, Swim Transformation and a custom-built CNN. Each model is trained and fine-tuned on the dataset to classify images into their respective disease categories. Performance is measured using accuracy, precision, recall, and F1-score metrics. The goal is to identify the most effective model for accurate and reliable disease classification, which can assist farmers and agricultural experts in timely diagnosis and intervention.

Keywords: Wheat Disease Detection, Deep Learning, CNN, ResNet50, InceptionNet, DenseNet201, VGG19, NASNetLarge, MobileNet, CNN, Vit, Swim Transformation Agricultural AI, Plant Pathology, Image Classification, Precision Agriculture, Wheat Plant Dataset, Transfer Learning.