Automated Plant Disease Detect System

Abstract

Problem: In agricultural practices, early and accurate detection of plant diseases is crucial for preventing crop losses and ensuring food security. However, existing plant disease detection systems largely depend on high-quality image inputs, limiting their accessibility and accuracy in rural or resource-constrained environments where farmers often capture low-quality images with inexpensive devices. The lack of focus on enhancing these low-quality images results in poor detection performance, leading to misdiagnosis and ineffective treatment recommendations. Methodology: To address this challenge, we propose a plant disease detection system that integrates advanced image processing techniques to enhance low-quality images, making the system more accessible and reliable for farmers. The system applies edge-preserving denoising, contrast enhancement, and GAN-based super-resolution to improve the quality of low-resolution images while preserving critical disease features.