Practical Deep Learning for Plant Disease Detection: Designing Lightweight Models from Image Classification to Edge Deployment

Artificial Intelligence is transforming agriculture, enabling faster, more accurate, and more accessible plant disease diagnosis. This book provides a practical introduction to building efficient deep learning models for plant disease detection using modern computer vision techniques. Drawing on research conducted at Bishop's University and a peer-reviewed publication in MDPI Electronics, the book explores the complete development pipeline—from dataset preparation and transfer learning to attention mechanisms, model evaluation, TensorFlow Lite deployment, and edge AI applications. Readers will gain practical insight into MobileNetV2, Convolutional Block Attention Module (CBAM), and lightweight deep learning architectures designed for resource-constrained devices. Designed for students, researchers, engineers, and AI practitioners, this book bridges the gap between academic research and real-world implementation, providing the knowledge required to develop intelligent agricultural solutions for precision farming and sustainable food production.