Developed an end-to-end deep learning system to automatically detect and classify crop diseases from leaf images using Convolutional Neural Networks (CNN).

The project focuses on assisting farmers and agricultural stakeholders by enabling early and accurate disease detection, reducing crop loss and improving yield quality. The system was trained on labeled plant leaf images and optimized to handle real-world variations such as lighting conditions, background noise, and different stages of disease severity.

Key highlights:

Designed and trained a CNN-based image classification model for multi-class crop disease detection

Performed data preprocessing including image resizing, normalization, and augmentation to improve model generalization

Implemented model training, validation, and evaluation pipelines with performance metrics such as accuracy and loss curves

Integrated the trained model into an inference workflow capable of predicting diseases from new input images

Focused on practical deployment readiness for agricultural use cases

This project demonstrates hands-on experience in deep learning, computer vision, and applied AI for real-world problem solving in agriculture.