Plant Disease Diagnosis Research Articles

Enhancing plant leaf disease detection: Integrating krill herd optimization-surf features and deep belief network

A plant disease that attacks the leaf causes significant yield and market value losses. A professional plant pathologist should be able to visually identify the disease by looking at the affected plant leaves, but this is unlikely to result in a more accurate diagnosis. Disease symptoms should be immediately recognisable in order to stop the spread of the illness. To find plant diseases, steps should be taken using computer assisted technologies. Numerous methods for identifying plant diseases using machine learning (ML) and deep learning (DL) have been developed and tested in numerous studies. Machine learning has the disadvantages of having a small dataset, taking longer, and requiring more time for results interpretation. Deep learning is suggested as a solution to this. This study compares the effectiveness of both ML&DL for plant leaf disease identification with more recent investigations. The common deep learning technique involves utilising the Krill Herd Optimisation Algorithm (KHO) to segment images and the Speeded up Robust Features (SURF) to extract the images. The Artificial Bee Colony (ABC) then chooses the features. Then, a Deep Belief Network (DBN) can be used to classify the chosen image. Multiple diseases can be identified on the same leaf using this method. This study demonstrates that deep learning outperforms machine learning in terms of results. The outcome demonstrates that the deep learning method is superior for the diagnosis of plant disease when there is sufficient data available. Using this technique, the validity and consistency were also examined.

Enhanced Deep Learning Architecture for Rapid and Accurate Tomato Plant Disease Diagnosis

Deep neural networks have demonstrated outstanding performances in agriculture production. Agriculture production is one of the most important sectors because it has a direct impact on the economy and social life of any society. Plant disease identification is a big challenge for agriculture production, for which we need a fast and accurate technique to identify plant disease. With the recent advancement in deep learning, we can develop a robust and accurate system. This research investigated the use of deep learning for accurate and fast tomato plant disease identification. In this research, we have used individual and merged datasets of tomato plants with 10 diseases (including healthy plants). The main aim of this work is to check the accuracy of the existing convolutional neural network models such as Visual Geometry Group, Residual Net, and DenseNet on tomato plant disease detection and then design a custom deep neural network model to give the best accuracy in case of the tomato plant. We have trained and tested our models with datasets containing over 18,000 and 25,000 images with 10 classes. We achieved over 99% accuracy with our custom model. This high accuracy was achieved with less training time and lower computational cost compared to other CNNs. This research demonstrates the potential of deep learning for efficient and accurate tomato plant disease detection, which can benefit farmers and contribute to improved agricultural production. The custom model’s efficient performance makes it promising for practical implementation in real-world agricultural settings.

Advancements in Agricultural Technology: A Comprehensive Review of Machine Learning and Deep Learning Approaches for Crop Management and Disease Detection

Traditional agricultural practices often lack personalized guidance for farmers, which leads to poor crop choices, wasteful fertiliser use, and inadequate disease control. As a result, sustainability and productivity decline. In order to address these issues, this review examines the developments in agricultural technology, with a focus on the fusion of deep learning and machine learning techniques. We look at techniques like ensemble modelling, which optimises crop selection and fertiliser consumption depending on soil properties, and advanced image processing methods, which use leaf images to diagnose plant diseases accurately. Our goal in conducting this study is to provide light on how agricultural technology is developing and how it affects contemporary farming methods. We emphasise the major trends, approaches, and developments in the field of agricultural technology by examining a variety of research papers covering many elements of the subject. Our thorough analysis highlights the potential of deep learning and machine learning techniques to transform agricultural disease diagnosis, fertiliser selection, and crop management. With this investigation, we hope to add to the current conversation about using technology to solve the urgent problems facing the agriculture industry and, in the process, open the door for more effective and sustainable farming methods in the future

Dissecting Diagnostic and Management Strategies for Plant Viral Diseases: What Next?

Recent advancements in molecular biology have revolutionized plant disease diagnosis and management. This review focuses on disease diagnosis through serological techniques, isothermal amplification methods, CRISPR-based approaches, and management strategies using RNA-based methods. Exploring high-throughput sequencing and RNA interference (RNAi) technologies like host-induced gene silencing (HIGS) and spray-induced gene silencing (SIGS), this review delves into their potential. Despite the precision offered by RNAi in pest and pathogen management, challenges such as off-target effects and efficient dsRNA delivery persist. This review discusses the significance of these strategies in preventing aphid-mediated plant virus transmission, emphasizing the crucial role of meticulous dsRNA design for effective viral RNA targeting while minimizing harm to plant RNA. Despite acknowledged challenges, including off-target effects and delivery issues, this review underscores the transformative potential of RNA-based strategies in agriculture. Envisaging reduced pesticide dependency and enhanced productivity, these strategies stand as key players in the future of sustainable agriculture.

Application of image recognition technology based on deep learning in plants disease detection and diagnosis

With increasing demographic trends, the world will likely confront a looming food crisis in the coming decades. This paper points out the world's food crisis brought by the increasing population and the agricultural sector's challenges. Among them, the increase in plant diseases is considered one of the leading causes of agricultural inefficiency and food production problems. For example, in many countries, cash crops such as jute, pomegranate, and tomato have been severely affected by plant diseases, resulting in reduced yields and, thus, increased economic losses. Traditional disease detection methods, such as manual visual inspection and laboratory analysis, are inaccurate and time-consuming, requiring a lot of manpower and capital investment. In recent years, researchers have begun to apply deep learning-based image recognition technology to detect and diagnose plant diseases to improve accuracy and efficiency. This paper will lay the foundation for further research by summarizing the existing research and analyzing the advantages and applicability of different application methods.

Deep Learning for Automated Diagnosis of Plant Diseases: A Technological Approach

Deep Learning for Automated Diagnosis of Plant Diseases: A Technological Approach

PDSE-Lite: lightweight framework for plant disease severity estimation based on Convolutional Autoencoder and Few-Shot Learning.

Plant disease diagnosis with estimation of disease severity at early stages still remains a significant research challenge in agriculture. It is helpful in diagnosing plant diseases at the earliest so that timely action can be taken for curing the disease. Existing studies often rely on labor-intensive manually annotated large datasets for disease severity estimation. In order to conquer this problem, a lightweight framework named "PDSE-Lite" based on Convolutional Autoencoder (CAE) and Few-Shot Learning (FSL) is proposed in this manuscript for plant disease severity estimation with few training instances. The PDSE-Lite framework is designed and developed in two stages. In first stage, a lightweight CAE model is built and trained to reconstruct leaf images from original leaf images with minimal reconstruction loss. In subsequent stage, pretrained layers of the CAE model built in the first stage are utilized to develop the image classification and segmentation models, which are then trained using FSL. By leveraging FSL, the proposed framework requires only a few annotated instances for training, which significantly reduces the human efforts required for data annotation. Disease severity is then calculated by determining the percentage of diseased leaf pixels obtained through segmentation out of the total leaf pixels. The PDSE-Lite framework's performance is evaluated on Apple-Tree-Leaf-Disease-Segmentation (ATLDS) dataset. However, the proposed framework can identify any plant disease and quantify the severity of identified diseases. Experimental results reveal that the PDSE-Lite framework can accurately detect healthy and four types of apple tree diseases as well as precisely segment the diseased area from leaf images by using only two training samples from each class of the ATLDS dataset. Furthermore, the PDSE-Lite framework's performance is compared with existing state-of-the-art techniques, and it is found that this framework outperformed these approaches. The proposed framework's applicability is further verified by statistical hypothesis testing using Student t-test. The results obtained from this test confirm that the proposed framework can precisely estimate the plant disease severity with a confidence interval of 99%. Hence, by reducing the reliance on large-scale manual data annotation, the proposed framework offers a promising solution for early-stage plant disease diagnosis and severity estimation.

Utilizing Fuzzy Logic in Precision Agriculture: Techniques for Disease Detection and Management

Utilizing Fuzzy Logic in Precision Agriculture: Techniques for Disease Detection and Management

Detecting Plant Diseases at Scale: A Distributed CNN Approach with PySpark and Hadoop

In modern agriculture, detecting and diagnosing plant diseases are pivotal for crop health and yield optimization. This transformative initiative leverages cutting-edge technology to reshape the field. Data integrity is paramount for our machine learning model's success. We meticulously collect verified data from Kaggle, then preprocess the dataset of 2000 diverse images. Uniformly resizing them to 150px and batching them in groups of 32 optimizes training speed and memory usage.The model's innovation lies in its Convolutional Neural Networks (CNNs) powered by PySpark for efficient distributed data processing. Integration of Tkinter bridges technology and user-friendliness, offering farmers intuitive disease detection solutions through a graphical interface. This triad of CNNs, PySpark, and Tkinter achieves an outstanding average accuracy of 95.76%, adept at distinguishing diseased from healthy leaves. Embracing this innovation promises to elevate agricultural practices and enhance crop productivity, marking a milestone in modern agriculture.

Effects of single and multiple nucleotide mutations on loop-mediated isothermal amplification.

Testing is pivotal for early identification of disease and subsequent infection control. Pathogens' nucleic acid sequence can change due to naturally-occurring genetic drift or intentional modification. Because of the reliance on molecular assays for human, animal, and plant disease diagnosis, we must understand how nucleotide mutations affect test accuracy. Primers designed against original lineages of a pathogen may be less efficient at detecting variants with genetic changes in priming regions. Here, we made single- and multi-point mutations in priming regions of a model SARS-CoV-2 template that was used as input for a loop-mediated isothermal amplification (LAMP) assay. We found that many of the modifications impacted assay sensitivity, amplification speed, or both. Further research exploring mutations at every position in each of the eight priming regions should be conducted to evaluate trends and determine generalizability.

Research of Plant Disease Diagnostic Methods Using Deep Learning

The article explores the use of convolutional neural networks (CNNs) in the diagnosis and identification of plant diseases and pests. Various methods of plant disease diagnosis, features of datasets, and challenges in this research direction are considered. The article discusses a five-step methodology for determining plant diseases, including data collection, preprocessing, segmentation, feature extraction, and classification. Different deep learning architectures enabling fast and efficient plant disease diagnosis are investigated. Innovative trends and issues in this field requiring further research and attention from the scientific community are highlighted.

Innovative Methods for Diagnosis Evergreen Utilizing Ultraspectral Image Inspection: A Review

Plant diseases result in large financial losses in the global agricultural production industry. Regarding crop production, early disease detection, measurement, and identification are essential for the focused use of control measures. Extensive scientific research is now underway to provide novel hyperspectral technology-based solutions for plant disease diagnosis. By looking at the reflectance spectrum of plant tissue, you can tell the difference between healthy and sick plants, figure out how bad the disease is, name different pathogen species, and find early signs of biotic stress, even when the symptoms are not readily apparent to the unaided eye during the incubation phase. The review covers of fundamentals determining the reflectance spectrum of plant tissue. There is a discussion and evaluation of the potential applications of several kinds of hyperspectral Sensor technology and platforms for plant disease examination. Hyperspectral analysis, a relatively new field, employs techniques from image analysis and optical spectroscopy to measure physiological and morphological characteristics simultaneously. The following are the key phases of hyperspectral data analysis: modeling and data analysis; data extraction and processing; and picture collection and pre-processing. The algorithms and techniques used in each step are listed, then examine the primary uses of hyperspectral sensors in plant disease diagnosis, which include illness detection, disease classification and identification, damage assessment, andgenetic resistance evaluation. An extensive analysis of scholarly literature highlights the advantages of hyperspectral technology in investigating pathogen-plant interactions across various measurement scales. Despite significant advancements in plant disease monitoring using hyperspectral technology over the past few decades, several unresolved technical issues still hinder their practical application. Finally, we explore the issues and future directions for the application of new technology in agriculture.

Application of quantum computing in image processing for recognition of infectious diseases of wheat

This study is devoted to the development and application of quantum methods in the field of diagnostics of infectious diseases of wheat. Taking into account the relevance of the problem of agriculture and the need to improve the efficiency of plant disease control, the work proposes a new approach based on the combined use of quantum computing, image processing and machine learning. Quantum image processing techniques have been applied to improve contrast, filter noise, and analyze key features of infectious diseases in the early stages of their development. The developed quantum machine learning models demonstrate high ac-curacy in image classification, which contributes to earlier and more accurate detection of diseases. The study results highlight the effectiveness of quantum methods in agriculture and provide new tools for more accurate diagnosis of infectious plant diseases. The prospects for introducing this approach into agriculture mean the possibility of improving yields, reducing the use of chemicals and ensuring food security.

Recent advances in biosensors for screening plant pathogens.

Worldwide, plant pathogens have been a considerably important cause of economic loss in agriculture especially in the decades of agricultural intensification. The increasing losses in agriculture due to biotic plant diseases have drawn attention towards the development of plant disease analyzing methods. In this context, biosensors have emerged as significantly important tools which help farmers in on-field diagnosis of plant diseases. Compared to traditional methods, biosensors have outstanding features such as being highly sensitive and selective, cost-effective, portable, fast and user-friendly operation, and so on. There are three common types of biosensors including electrochemical, fluorescent, and colorimetric biosensors. In this review, some common biotic plant diseases caused by fungi, bacteria, and viruses are first summarized. Then, current advances in developing biosensors are discussed.

Transforming agriculture with artificial intelligence: Methods, applications and limitations for diagnosing plant diseases

Transforming agriculture with artificial intelligence: Methods, applications and limitations for diagnosing plant diseases

针对玉米叶片病斑图像的人工智能识别方法研究

Maize eyespot and maize curvularia leaf spot are two diseases that often occur on maize leaves. Because of the similarity of the shape and structure, it is difficult to identify the two diseases just relying on the observation of the growers. For the harmfulness and prevention methods are different, it would cause great loss if the disease can't be identified accurately. To address this issue, this paper first employs a connected region feature recognition method to design an automated lesion cropping process after acquiring leaf images with several lesions. Subsequently, a lesion recognition model based on the AlexNet architecture is built and subjected to five-fold cross-validation experiments. The results indicate that the model achieves a comprehensive recognition accuracy exceeding 99%. To further comprehend model characteristics, an analysis of the recognition accuracy and its fluctuations is conducted, revealing that the fractal growth and biological characteristics of the lesions may influence the recognition results. Moreover, the distribution of model parameters could be a potential reason for fluctuations in recognition accuracy rates with increasing number of iterations. This paper could offer valuable reference and support for the intelligent identification and diagnosis of maize and other plant diseases.

Precision Agriculture through Deep Learning Algorithms for Accurate Diagnosis and Continuous Monitoring of Plant Diseases

For sustainable food production, precision agriculture is essential, and one of its main tenets is the precise identification and ongoing surveillance of plant diseases. Conventional approaches to illness monitoring and detection are frequently labour-intensive, time-consuming, and dependent on visual inspection, which increases the risk of misidentifying diseases. Deep learning algorithms have surfaced as a potentially effective way to tackle these issues. In this study, we introduce a novel method for precision agriculture that improves plant disease diagnostic accuracy and offers continuous monitoring by utilising deep learning algorithms. Our research uses cutting-edge convolutional neural networks (CNNs) and ResNet50 to precisely identify illness symptoms in plant photos. The proposed deep learning model is trained on an extensive dataset of plant photos illustrating a range of illnesses, enabling it to identify minute visual cues that human observers might overlook. Compared to previous ML methods, the model's accuracy in detecting diseases is higher, which lowers the possibility of misdiagnosis and facilitates early intervention to minimise crop damage. By placing cameras and sensors in the fields, proposed system provides continuous monitoring in addition to precise diagnosis. The proposed deep learning model processes the real-time data and photos of the crops that are captured by these devices.

Rice Leaf Disease Classification with Machine Learning: An Approach Using Nu-SVM

This study explores the application of machine learning for classifying rice leaf diseases, employing the Nu-Support Vector Machine (Nu-SVM) algorithm, analyzed through a 5-fold cross-validation approach. The research focuses on distinguishing between healthy leaves and those affected by BrownSpot and LeafBlast diseases. The dataset, comprising segmented rice leaf images processed using Sobel edge detection and Hu Moments feature extraction, is utilized to train and test the model. Results indicate a moderate level of accuracy (52.12% to 53.81%) across the cross-validation folds, with precision and recall metrics demonstrating variability and highlighting the challenges in precise disease classification. Despite this, the model maintains a consistent ability to identify true positives. The study contributes to the field of precision agriculture by showcasing the potential and limitations of using machine learning for plant disease diagnosis. It underscores the need for advanced image processing techniques and diverse feature extraction methods to enhance model performance. The findings are pivotal for developing more effective, automated diagnostic tools in agriculture, thereby aiding in better disease management and potentially improving crop yields. This research serves as a foundational step towards integrating machine learning in agricultural disease detection, emphasizing its importance in sustainable farming practices.

Processing Plant Diseases Using Transformer Model

Agriculture faces challenges in achieving high-yield production while minimizing the use of chemicals. The excessive use of chemicals in agriculture poses many problems. Accurate disease diagnosis is crucial for effective plant disease detection and treatment. Automatic identification of plant diseases using computer vision techniques offers new and efficient approaches compared to traditional methods. Transformers, a type of deep learning model, have shown great promise in computer vision, but as the technology is still new, many vision transformer models struggle to identify diseases by examining the entire leaf. This paper aims to utilize the vision transformer model in analyzing and identifying common diseases that hinder the growth and development of plants through the plant leave images. Besides, it aims to improve the model's stability by focusing more on the entire leaf than individual parts and generalizing better results on leaves not in the image center. Added features such as Shift Patch Tokenization, Locality Self Attention, and Positional Encoding help focus on the whole leaf. The final test accuracy obtained is 89.58%, with relatively slight variances in precision, accuracy, and F1 score across classes, as well as satisfactory model robustness towards changes in leaf orientation and position within the image. The model's effectiveness shows the vision transformer's potential for automated plant disease diagnosis, which can help farmers take timely measures to prevent losses and ensure food security.

Processing Plant Diseases Using Transformer Model

Agriculture faces challenges in achieving high-yield production while minimizing the use of chemicals. The excessive use of chemicals in agriculture poses many problems. Accurate disease diagnosis is crucial for effective plant disease detection and treatment. Automatic identification of plant diseases using computer vision techniques offers new and efficient approaches compared to traditional methods. Transformers, a type of deep learning model, have shown great promise in computer vision, but as the technology is still new, many vision transformer models struggle to identify diseases by examining the entire leaf. This paper aims to utilize the vision transformer model in analyzing and identifying common diseases that hinder the growth and development of plants through the plant leave images. Besides, it aims to improve the model's stability by focusing more on the entire leaf than individual parts and generalizing better results on leaves not in the image center. Added features such as Shift Patch Tokenization, Locality Self Attention, and Positional Encoding help focus on the whole leaf. The final test accuracy obtained is 89.58%, with relatively slight variances in precision, accuracy, and F1 score across classes, as well as satisfactory model robustness towards changes in leaf orientation and position within the image. The model's effectiveness shows the vision transformer's potential for automated plant disease diagnosis, which can help farmers take timely measures to prevent losses and ensure food security.