Crop Classification using Convolutional Neural Network

- Crop Classification using CNN - A Multi-Model Approach for Crop Classification and Health Assessment Using Convolutional Neural Networks and GPT Integration Crop classification and health assessment are critical tasks in precision agriculture, aimed at improving yield and minimizing losses. In this research, we propose a multi-model pipeline leveraging Convolutional Neural Networks (CNNs) to classify crops and assess their health conditions based on leaf images. The pipeline consists of two primary models: (1) a detection and classification model to identify crop types (e.g., potato, tomato) and (2) a health condition classification model to diagnose plant health (e.g., healthy, early blight, late blight). The pipeline integrates a Generative Pre-trained Transformer (GPT) API to generate actionable quality summaries based on the model outputs. Extensive experiments were conducted to compare YOLOv5, ResNet-50, EfficientNet-B0, and other models, supported by performance metrics, real-world applicability, and insights from generated summaries. Key Words: Deep Learning in Agriculture, Convolutional Neural Networks (CNNs), Plant Disease Detection, Generative AI for Crop Analysis, Precision Agriculture.