Paper Title
A Survey of Pretrained Deep Learning (DL) Models for Plant Disease Identification

Abstract
Identification of plant diseases is crucial to maintaining food security by enabling initial detection and prevention of crop losses. Deep learning, particularly the use of pretrained models, has emerged as a formidable method for automated image-based disease identification. This paper presents a comprehensive survey of pretrained deep learning (DL)models for identifying plant diseases. We focus on popular architectures such as ResNet[1], VGG, and Inception, examining their applications and performance in this domain. The survey analyzes the intenseness and limitations of each model, considering factors like accuracy, computational efficiency, and data requirements. Furthermore, we discuss the challenges and future directions in leveraging pretrained models for more robust and accurate diagnosis of plant diseases. Keywords - Plant Disease Identification, ResNet, VGG, Inception, DenseNet and Deep learning (DL)