Top Research Papers on Plant Disease Detection

This project is based on deep convolutional neural networks which enhances the accuracy and training efficiency and will help many farmers who are uneducated to get correct information about diseases and help increase their yield.

With the use of the proposed algorithm, farmers will be able to identify diseases in their early stages, diagnose leaf diseases, and then control the crop as needed to maintain the health and safety of plants.

This research explores the transformative capabilities of Deep Learning models, primarily focusing on Convolutional Neural Networks (CNNs) and MobileNet architectures in the early and precise identification of plant ailments, by incorporating eXplainable Artificial Intelligence through GradCAM.

This work proposes a cardamom plant disease detection approach using the EfficientNetV2 model and results showed that the proposed approach achieved a detection accuracy of 98.26%.

An analysis of various methods for detecting image processing plant leaf diseases and how the denoising step can be achieved by application of different filters is presented.

This work aims to develop a digital solution to the problem of Plant Disease Detection by training the fastest single-stage object detection model, YOLOv7, on the labeled PlantDoc Dataset, and achieves a significantly higher mean average precision.

This research study has conducted disease classification based on tomato leaves by employing a pre-trained deep CNN in conjunction with the residual network, demonstrating a remarkable result with an accuracy of 96.35%.

The best way to forestall misfortune in gather and number of cultivating items is through sickness identification. Plant sickness is not characterized as an illness that can be recognized by actual irregularities of the plant (like shrinking of leaves). Ill-advised upkeep or confirmation of plant illness can make colossal misfortunes to the ranchers. Plant wellbeing checking and sickness location are vital for maintainable farming. It is undeniably challenging to detect the illness physically for goliath regions. It requires more labor who work in plant sicknesses and furthermore requires real...

Agriculture is an important part in the human lives and economy of the countries. Agriculture based countries like India are greatly dependent on their agricultural outcome for feeding the large population. Crop yields plays a major factor in the economy of every country. Agricultural production and economic development are closely connected. Moreover, agriculture provides the vital food to feed all living creatures on earth. Plant diseases are a significant threat to farmers, food production and economic well-being of the country. Significant research in this domain is required to protect the...

New datasets for food grains specifically for rice, wheat, and maize are developed to address the identified challenges and a new convolutional neural network model is proposed trained from scratch on all three food grain datasets developed.

A mobile application to identify plant disease and connect them with scientists and it is hoped it will help all farmers to do quality control, especially for the old age farmers.

This article explains how to use DL models to display a variety of plant diseases, allowing for improved efficiency in detecting plant illnesses even before issues emerge.

The goal of this paper is to create a Disease Recognition Model that is supported by leaf image classification and utilizing image processing with a convolutional neural network, a form of artificial neural network that is used in image recognition.

An ensemble model based on Random Forest and K-Nearest Neighbor for the detection of plant diseases from the leaves is proposed and it is revealed that the proposed approach outperformed SVM.

A novel plant disease detection technique based on deep learning is proposed in this work and significantly detect diseases and achieves an accuracy of respectively.

A review of various existing approaches in disease detection of various plants and vegetables is done in order to find which algorithm works better and provides higher accuracy and this can be made using various models of machine learning.

An efficient and small deep learning-based framework (E-GreenNet) is proposed for automatically detecting early illnesses and revealing extremely high discriminative scores against the state-of-the-art SOTA.

A system involving a standard smartphone to predict the plant diseases using machine learning approach that potentially benefits the cultivators as it is capable to detect the diseases without minimal human intervention with prompt results.

This review provides the research progress of deep learning technology in the field of crop leaf disease identification in recent years and presents the current trends and challenges for the detection of plant leaf disease using deep learning and advanced imaging techniques.

This study used deep learning techniques to categorize and detect plant leaf diseases in photos taken from the Plant Village dataset, focusing on potato plants because it is the most common type of plant in the world, particularly in Pakistan.

This study presents research on the detection of plant diseases and pests based on three aspects of the classification network, detection network, and segmentation network in recent years, and summarizes the advantages and disadvantages of each method.

This work described the innovative solution that provides efficient disease detection and deep learning with CNN has achieved great success in the classification of various plant leaf diseases.

A low-cost cross platform mobile application with machine learning features has been implemented using Flutter for users to capture diseased images of leaves and get the plant, disease name and cure for fungal diseases in Mauritius.

The aim is to identify the plant diseases using image analysis, and the various machine learning algorithms used to determine whether a plant is infected or not with a disease are discussed in this study.

The goal of this paper is to create a Disease Recognition Model that is supported by leaf image classification that is utilizing image processing with a Convolution neural network (CNN).

This study presents a framework for leveraging AI/ML techniques to enhance plant disease diagnosis and contribute to global food security efforts using the Inception V3 architecture and data augmentation techniques.

An innovative approach that integrates machine learning and image processing techniques is introduced that identifies diseases based on key factors such as leaf color, damage extent, area, and texture parameters and ensures precise disease detection with minimized computational complexity and reduced prediction time.

PlantDoc web application successfully helps to identify plant diseases of various plants by analyzing plant leaf image and suggests cure to treat it and helps in treatment of plants timely which helps to stop the further spread of dis-ease and provides cure.

This research investigates the utilization of the YOLOv4 algorithm for detecting and identifying plant leaf diseases and underscores the capabilities of YOLOv4 as a sophisticated tool for accurate disease prediction.

The SVM, Random Forest classifier, and CNN are found to be efficient and accurate methods of classification and the potential for automation and smartphone-assisted diagnosis is covered.

The main aim of the proposed work is to find a solution to the problem of 38 different classes of plant diseases detection using the simplest approach while making use of minimal computing resources to achieve better results compared to the traditional models.

The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy.

Pre-trained Convolution Neural Networks (AlexNet, VGG16, VGG19) have been utilised along with transfer learning for detecting plant diseases and modified AlexNet performed best and got 96.63% as accuracy, 92 % as precision, 91 % as recall, and 91 % as f1-score.

A computer vision approach using the latest state of art You Only Look Once (YOLO) algorithms in developing an expert system, which can accurately identify numerous plant diseases from a diverse set of plant species is introduced.

The results of this study show that the EfficientNet B1 model suggested worked remarkably well, with a 99% accuracy rate, which emphasizes how well the model can classify plant illnesses, which could be helpful for farmers and other agriculture specialists.

The results of this study demonstrate the effectiveness of using ensemble learning for plant disease detection and the potential for such a system to assist in the accurate and efficient identification of plant diseases.

Results show that for plant disease detection, deep learning outperforms traditional machine learning algorithms while visible range images are more widely used compared to spectral images.

FieldPlant is suggested as a dataset that includes 5,170 plant disease images collected directly from plantations and evaluated state-of-the-art classification and object detection models and found that classification tasks on FieldPlant outperformed those on PlantDoc.

This paper presents a plant disease detection and classification method using YOLOv3 (You Only Look Once) model to design an Internet-of-Things (IoT) device that achieves an average of 96.92% of classification accuracy while detecting plant disease for three different classes.

The globe and more particularly the economically developed regions of the world are currently in the era of the Fourth Industrial Revolution (4IR). Conversely, the economically developing regions in the world (and more particularly the African continent) have not yet even fully passed through the Third Industrial Revolution (3IR) wave, and Africa’s economy is still heavily dependent on the agricultural field. On the other hand, the state of global food insecurity is worsening on an annual basis thanks to the exponential growth in the global human population, which continuously heightens the fo...

Empirical results show that the Scaled-YOLOv4 model is a well suitable object detection model providing a real-time solution in detecting even small infected regions of the plant leaves within less time duration.

Agriculture production is one of the fundamental contributors to a nation's economic development. Every year, plant diseases result in significant crop losses that threaten the global food supply chain. Early estimation of plant diseases could play an essential role in safeguarding crops and fostering economic growth. Recently, hyperspectral imaging techniques have emerged as powerful tools for early disease detection, as they have demonstrated capabilities to detect plant diseases from tissue to canopy levels. This article provides an extensive overview of the principles, types, and operating...

Agriculture is demographically the broadest economic sector in India and plays a significant role in the overall socio economic fabric of India. Several diseases affect plants and cause economic, social and economic losses. So detection of diseases accurately and giving control measures timely will increase growth of agriculture in India. The proposed system identifies the disease by observable patterns of particular plant; here SVM used for classification. This is an efficient and accurate method for automatic disease detection in plants.

Experimental results demonstrate the effectiveness of the proposed approach in achieving high accuracy for plant disease detection at the end of the 11th day after plant inoculation.

This investigation aims to create a sophisticated learning model that can tell a plant's illness apart from images of its leaves, using Convolution Brain Organization to do move training to complete deep learning.

A CNN-based method for earlier disease detection in plants is suggested and an image of the plant's diseased portions is obtained, compared to the desired dataset, and used to predict the disease and provide subsequent treatment options.

A technique to classify plant disease by images of the plants by using transfer learning models, which will be used to put out a comparative analysis to assert the viability of using the defined methods in order to visually categorize the plant diseases.

Egypt is an agricultural country where the possibility of knowledge cultivation has been acquired where the field conditions are controlled and checked using the self-acknowledgement of the malady relying upon the recognizable proof of the manifestations of infection.

The main aim of this paper is to identify the diseased and healthy leaves of distinct plants by extracting features from input images using CNN algorithm, and it is observed that the proposed system consumes an average time of 3.8 seconds for identifying the most relevant class for images from the datasets.

Plant diseases of an infectious nature are the reason for major economic losses in agriculture throughout the world. The early, rapid and non-invasive detection of diseases and pathogens is critical for effective control. Optical diagnostic methods have a high speed of analysis and non-invasiveness. The review provides a general description of such methods and also discusses in more detail methods based on the scattering and absorption of light in the UV, Vis, IR and terahertz ranges, Raman scattering and LiDAR technologies. The application of optical methods to all parts of plants, to a large...