Recent Papers

Abstract:A large portion of crops are lost to plant diseases each year worldwide. In this study, The application for detecting and classifying plant disease using deep learning object detection model was developed. The proposed the application utilizes Faster CNN object detector with Inception-v2 backbone network to achieve robust and efficient detection.This paper presents a method for detecting and classifying tomato leaf diseases using a CNN model and Learning Vector Quantization (LVQ) algorithm. The method uses color information and applies filters to three channels based on RGB components. The proposed application can serve as an aid to farmers and crop growers who have little or no knowledge about plant diseases for early disease detection and control and therefore can reduce losses and prevent further spreading of the disease.Keywords:Plant pathology,Image-based diagnosis,Plant health monitoring, Early disease detection, Deep learning model.Introduction:plant disease detection applications are transforming agriculture by providing efficient, accurate, and scalable solutions for disease management. They represent a critical component in the move towards precision agriculture, ensuring healthier crops and more sustainable farming practices. Plant disease detection applications are pivotal in modern agriculture, leveraging advanced technologies to identify and manage plant diseases efficiently. The early detection of plant diseases is crucial for preventing significant crop losses, ensuring food security, and minimizing the use of chemical treatments. These applications integrate various tools and techniques, from traditional methods like visual inspection to cutting-edge technologies such as machine learning, image processing, and remote sensing.Plant diseases cause major production and economic losses in agriculture and forestry. For example, soybean rust (a fungal disease in soybeans) has caused a significant economic loss and just by removing 20% of the infection, the farmers may benefit with an approximately 11 million-dollar profit (Roberts et al., 2006). The bacterial, fungal, and viral infections, along with infestations by insects result in plant diseases and damage. Many such microbial diseases with time spread over a larger area in groves and plantations through accidental introduction of vectors or through infected plant materials. Another route for the spread of pathogens is through ornamental plants that act as hosts. These plants are frequently sold through mass distribution before the infections are known. An early disease detection system can aid in decreasing such losses caused by plant diseases and can further prevent the spread of diseases.In the present paper, advanced techniques of ground-based disease detection that could be possibly integrated with an automated agricultural vehicle are reviewed. In ground-based disease detection studies, both field-based and laboratory-based experiments are discussed in this paper. The field-based studies refer to studies that involve spectral data collection under field conditions, whereas laboratory-based studies refer to data collection under laboratory conditions. The laboratory-based experiments provide strong background knowledge (such as the experimental protocol and statistical algorithm for classification) for the field-based applications.The motivation for preparing this survey stems from the fact that DL in agriculture is a recent, modern and promising technique with growing popularity, while advancements and applications of DL in other domains indicate its large potential. The fact that today there exists at least 40 research efforts employing DL to address various agricultural problems with very good results.The traditional disease diagnosis method mainly judges the health status or disease type of crops. It guides agricultural production by manually observing the color, size, and disease spot shape of crop leaves, which has problems, such as high professional requirements, long diagnosis time, and low work efficiency. Based on this, scholars are committed to identifying the characteristics of crop leaves and other characteristics through network models to achieve rapid detection and classification of diseases. At the same time, they also continue to expand the types of datasets to improve the scope of application of the method, which plays a vital reference and guiding role in the quality and output. The detection speed, accuracy, and recognition category of the model are improved by using DarkNet for feature detection after the convolutional layer. the results of the application of the proposed models for plant disease detection and diagnosis.

Copyright © 2024 Sharvari Gajanan Malve. This is an open access article distributed under the Creative Commons Attribution License.