Review Paper On Crop Disease Diagnosis Model Using Deep Hybrid Architecture With A New Segnet-Based Segmentation Model

Abstract

Crop diseases are a serious risk to the world's food supply, reducing agricultural productivity and causing substantial economic losses each year. Crop disease management, yield loss reduction, and sustainable farming practices all depend on early and precise diagnosis. Conventional approaches of disease diagnosis, which frequently depend on Visual examination and professional expertise, can be lengthy and prone to human error. In recent years, technological developments, including machine learning, image processing, and remote sensing—have revolutionized the field, offering more precise, rapid, and scalable solutions. This work explores current methodologies for crop disease diagnosis, highlights emerging technologies, and discusses the potential of integrating artificial intelligence to improve accuracy and accessibility in agricultural disease management.