Early Detection Of Plant Diseases Research Articles

Effects of metal nanoparticle-mediated treatment on seed quality parameters of different crops.

The increasing population of the world requires novel techniques to feed everyone, which can replace or work along with traditional methods to increase production of agricultural crops. In recent times, nanotechnology is considered as a promising and emerging approach to be incorporated in agriculture to improve productivity of different crops by the administration of nanoparticles through seed treatment, foliar spray on plants, nano-fertilizers for balanced crop nutrition, nano-herbicides for effective weed control, nanoinsecticides for plant protection, early detection of plant diseases and nutrient deficiencies using diagnostics kits, and nano-pheromones for effective monitoring of pests. Further, distinct nanoparticles with unique physicochemical and biological properties are used in agriculture to increase the percentage of seed germination, which is the initial step to increase the crop yield. In the context of agricultural crops, nanoparticles have both positive effects on seed quality parameters, such as germination percentage, seedling length, seedling dry weight and vigor indices, as well as negative impacts of causing toxicity toward the environment. Thus, the aim of this review article is to provide a comprehensive overview on the effects of super-dispersive metal powders, such as zinc, silver, and titanium nanoparticles on the seed quality parameters of different crops. In addition, the drawback of conventional seed growth enhancers, impact of metal nanoparticles toward seeds, and mechanism of nanoparticles to increase seed germination were also discussed.

Development of Concise Convolutional Neural Network for Tomato Plant Disease Classification Based on Leaf Images

Early detection of plant diseases is one of the main keys to handling diseases quickly and successfully. The purpose of this study is to find out a simpler CNN architecture and meet an acceptable compromise between accuracy and simplification to detect diseases in tomato plants based on leaf images. This simpler architecture will allow the development of standalone and independent system model in the field to classify and identify the tomato plants diseases in low price and limited resources. This proposed architecture was developed from the CNN architecture baseline and is intended to classify 10 classes of tomato leaves consist of one healthy class and 9 classes of leaves diseases taken from the Plant Village dataset. In this study, the performance of the proposed architecture and comparative architectures are examined in the same dataset. Comparative architectures used are some existing CNN architectures that are commonly used namely VGG Net, Shuffle Net and Squeeze Net. The results indicated that the proposed architecture can achieve competitive accuracy compared with the existing architecture while the proposed architecture is much shorter than the existing architecture and better in terms of performance time.

Molecular Approaches for Low-Cost Point-of-Care Pathogen Detection in Agriculture and Forestry.

Early detection of plant diseases is a crucial factor to prevent or limit the spread of a rising infection that could cause significant economic loss. Detection test on plant diseases in the laboratory can be laborious, time consuming, expensive, and normally requires specific technical expertise. Moreover, in the developing countries, it is often difficult to find laboratories equipped for this kind of analysis. Therefore, in the past years, a high effort has been made for the development of fast, specific, sensitive, and cost-effective tests that can be successfully used in plant pathology directly in the field by low-specialized personnel using minimal equipment. Nucleic acid-based methods have proven to be a good choice for the development of detection tools in several fields, such as human/animal health, food safety, and water analysis, and their application in plant pathogen detection is becoming more and more common. In the present review, the more recent nucleic acid-based protocols for point-of-care (POC) plant pathogen detection and identification are described and analyzed. All these methods have a high potential for early detection of destructive diseases in agriculture and forestry, they should help make molecular detection for plant pathogens accessible to anyone, anywhere, and at any time. We do not suggest that on-site methods should replace lab testing completely, which remains crucial for more complex researches, such as identification and classification of new pathogens or the study of plant defense mechanisms. Instead, POC analysis can provide a useful, fast, and efficient preliminary on-site screening that is crucial in the struggle against plant pathogens.

Optimal Deployment in Crowdsensing for Plant Disease Diagnosis in Developing Countries

In most of the developing countries, the economy is largely based on agriculture. The poor availability of skilled personnel and of appropriate supporting infrastructure, make crop fields vulnerable to the outbreak of plant diseases, possibly due to spreading viruses and fungi, or to adverse environmental conditions, such as drought. The mobile application PlantVillage Nuru, provides an invaluable tool for early detection of plant diseases and sustainable food production. A mobile device endowed with Nuru is a powerful mobile sensor: it analyzes plant images and uses an AI engine to recognize health issues. In this paper we propose a crowd-sensing framework, where Nuru is adopted at large scale in the farmer population. We tackle the device deployment problem, where device mobility is only partially controllable, mostly in an indirect manner, through incentives. We propose two problem formulations, and related algorithms, to minimize the number of required smartphones while providing sufficient geographical coverage. We study the proposed models in simulated as well as real scenarios, showing that they outperform current solutions in terms of monitoring accuracy and completeness, with lower cost. Then we describe the test-bed implementation, confirming the applicability of the proposed crowd-sensing framework in a real scenario in Kenya.

Deep Learning Model for Plant Disease Detection

Food is one of the basic needs of human being. We know that the population is rising enormously.so it is more important to feed such a huge population. But nowadays plants are largely affected with various types of diseases. If proper care should not be taken then it will show effect on quality of food products, quantity and finally on productivity of crops.. so, Early detection of plant disease is very essential, but it is very hard to farmers to monitor the crops manually it takes more processing time, huge amount of work, expensive and need expertised persons. Automatic detection of plant diseases helps the farmers to monitor the large fields easily,because our approach of using convolution neural networks provides a chance to discover diseases at the very early stage. By using Image Processing and machine learning models we can detect the plant diseases automatically but the accuracy is very less, early detection is also a major challenge. With the modern advanced developments in deep learning, in our project we have implemented the convolution neural networks(CNN) which comprises of different layers,by using those layers we can automatically detect and classify the diseases present in the plants. High Classification accuracy and more processing speed are the main advantages of our approach. After training the model on color, grayscale and segmented datasets our deep learning model will be capable of classifying a large number of different diseases and our project gives us the name of the disease that the plant has with its confidence level and also provides remedies for corresponding diseases.

New perspectives on plant disease characterization based on deep learning

The control of plant diseases is a major challenge to ensure global food security and sustainable agriculture. Several recent studies have proposed to improve existing procedures for early detection of plant diseases through modern automatic image recognition systems based on deep learning. In this article, we study these methods in detail, especially those based on convolutional neural networks. We first examine whether it is more relevant to fine-tune a pre-trained model on a plant identification task rather than a general object recognition task. In particular, we show, through visualization techniques, that the characteristics learned differ according to the approach adopted and that they do not necessarily focus on the part affected by the disease. Therefore, we introduce a more intuitive method that considers diseases independently of crops, and we show that it is more effective than the classic crop-disease pair approach, especially when dealing with disease involving crops that are not illustrated in the training database. This finding therefore encourages future research to rethink the current de facto paradigm of crop disease categorization.

Development of a Smell Biosensor System for Early Detection of Plant Diseases

Development of a Smell Biosensor System for Early Detection of Plant Diseases

Deep Learning Convolution Neural Network to Detect and Classify Tomato Plant Leaf Diseases

The tomato crop is an important staple in the ?market and it is one of the most common crops daily ?consumed. Plant or crop diseases cause reduction of quality and quantity of the production; therefore detection and classification of these diseases are very necessary. There are many types of diseases that infect ?tomato plant like (bacterial spot, late blight, sartorial leaf ?spot, tomato mosaic and yellow curved). Early detection of plant diseases increases production and improves its quality. Currently, intelligent ?approaches have been widely used to detect and classify these ?diseases. This approach helps the farmers to identify the types? of diseases that infect crop. The main object of the current work is ?to apply a modern technique to identify and classify the ?disease. Intelligent technique is based on using convolution ?neural network (CNN) which is a part of machine learning to ?obtain an early detection about the situation of plants. CNN ?method depends on feature extraction (such as color, leaves ?edge, etc.) from input image and on this basis the decision of ?classification is done. A Matlab m-file has been used to build ?the CNN structure. A dataset obtained from plant village has ?been used for training the network (CNN). The suggested ?neural network has been applied to classify six types of tomato ?leaves situation (one healthy and five types of leave plant ?diseases). The results show that the convolution neural ?network (CNN) has achieved a classification accuracy ??of 96.43%. Real images are used to validate the ability of ?suggested CNN technique for detection and classification, and obtained using a 5-megapixel camera from a real ?farm because most common diseases which infect the planet are similar.

Identification and Solutions for Grape Leaf Disease Using Convolutional Neural Network (CNN)

Crops are facing many diseases nowadays. These diseases lead to major damage and economic loss and hence early detection of disease is necessary to prevent the damage acquired by the crops. Fallacious diagnosis and severity of diseases lead to improper use of pesticides. Expert naked eye observation is the primary method used by plant disease detection and identification. Yet an examination of the naked eye is time-consuming, costly and takes a lot of effort. Classification is a system by which the leaf is classified according to its unique morphological characteristics. There are so many methods of classification, choosing a classification system is always a daunting task, because the consistency of the result differs according to different input data. Image processing is one of the commonly used methods for the identification and diagnosis of plant-leaf diseases. More effective methods are developed and proposed for the early detection of plant disease with the lowest processing period due to technological and scientific advances. The main aim of the proposed system is to detect the disease of the grape leaf using a neural network algorithm and to provide preventive or solutions to the user. Earlier one had to manually extract the features from images and pass it to different classification algorithm but CNN performs both image recognition and feature extraction. Compared to other algorithms the accuracy for image classification by CNN is more.

Machine Learning-Based Presymptomatic Detection of Rice Sheath Blight Using Spectral Profiles.

Early detection of plant diseases, prior to symptom development, can allow for targeted and more proactive disease management. The objective of this study was to evaluate the use of near-infrared (NIR) spectroscopy combined with machine learning for early detection of rice sheath blight (ShB), caused by the fungus Rhizoctonia solani. We collected NIR spectra from leaves of ShB-susceptible rice (Oryza sativa L.) cultivar, Lemont, growing in a growth chamber one day following inoculation with R. solani, and prior to the development of any disease symptoms. Support vector machine (SVM) and random forest, two machine learning algorithms, were used to build and evaluate the accuracy of supervised classification-based disease predictive models. Sparse partial least squares discriminant analysis was used to confirm the results. The most accurate model comparing mock-inoculated and inoculated plants was SVM-based and had an overall testing accuracy of 86.1% (N = 72), while when control, mock-inoculated, and inoculated plants were compared the most accurate SVM model had an overall testing accuracy of 73.3% (N = 105). These results suggest that machine learning models could be developed into tools to diagnose infected but asymptomatic plants based on spectral profiles at the early stages of disease development. While testing and validation in field trials are still needed, this technique holds promise for application in the field for disease diagnosis and management.

Disease detection in infected plant leaf by computational method

Plant diseases can directly affect the production hampering the economy significantly. Thus, early and correct detection of the disease is always a priority for an agriculture-dependent state. Of the many modern techniques of early detection of plant diseases, image processing has become a potential tool through which not only the disease can be detected early and correctly, but also it can be quantified successfully. The detection of two most important diseases of rice i.e., brown spot and rice blast was done through efficient computational method using a low complexity radial basis function neural network (RBFNN) classifier. The performance was analyzed using quality measures viz. accuracy, precision and recall and found to be 95%, 97% and 95%, respectively.

Automatic detection of rust disease of Lentil by machine learning system using microscopic images

<p>Accurate and early detection of plant diseases will facilitate mitigate the worldwide losses experienced by the agriculture area. MATLAB image processing provides quick and non-destructive means of rust disease detection. In this paper, microscopic image data of rust disease of <em>Lentil</em> was combined with image processing with depth information and developed a machine learning system to detect rust disease at early stage infected with fungus <em>Uromyces fabae</em> (Pers) de Bary. A novel feature set was extracted from the image data using local binary pattern (LBP) and HBBP (Brightness Bi-Histogram Equalization) for image enhancement. It was observed that by combining these, the accuracy of detection of the diseased plants at microscopic level was significantly improved. In addition, we showed that our novel feature set was capable of identifying rust disease at haustorium stage without spreading of disease. </p>

Nanotechnologies associated to floral resources in agri-food sector

El advenimiento de la nanotecnología en el sector agrícola está programado para impulsar la próxima revolución en la ingeniería agrícola. Sin embargo, existe una creciente necesidad de desarrollo de nuevas nanotecnologías que puedan trabajar sincrónicamente con diversos agroquímicos como fertilizantes, pesticidas, herbicidas y promotores de crecimiento para aumentar potencialmente la eficiencia de las tierras de cultivo, preservar los agroecosistemas y disminuir lo negativo Riesgos para la salud impuestas por las prácticas convencionales. En nanotecnología, los sistemas inteligentes de entrega que utilizan portadores a nanoescala como nanotubos de arcilla y nanotubos de carbono o nanopartículas como nanopartículas de sílice mesoporosas y nanopartículas de plata, podrían permitir no sólo la entrega precisa y específica de ingredientes funcionales sino también su difusión imparcial sobre las tierras de cultivo. La nanotecnología ha encontrado aplicaciones para la biorremediación del agua de riego y la escorrentía agrícola, la mejora de los rasgos de los cultivos mediante la manipulación genética de los genomas a nivel molecular y la detección de cantidades diminutas de contaminantes y factores de estrés, El seguimiento continuo del medio ambiente vegetal mediante el empleo de nanobiosensores. Los científicos están trabajando diligentemente para explorar nuevos sustitutos de las tecnologías convencionales. Los avances en nanotecnología podrían ayudarles a explorar nuevas fronteras y encontrar nuevas aplicaciones en el sector agrícola.

A method for automatic segmentation and splitting of hyperspectral images of raspberry plants collected in field conditions

Hyperspectral imaging is a technology that can be used to monitor plant responses to stress. Hyperspectral images have a full spectrum for each pixel in the image, 400–2500 nm in this case, giving detailed information about the spectral reflectance of the plant. Although this technology has been used in laboratory-based controlled lighting conditions for early detection of plant disease, the transfer of such technology to imaging plants in field conditions presents a number of challenges. These include problems caused by varying light levels and difficulties of separating the target plant from its background. Here we present an automated method that has been developed to segment raspberry plants from the background using a selected spectral ratio combined with edge detection. Graph theory was used to minimise a cost function to detect the continuous boundary between uninteresting plants and the area of interest. The method includes automatic detection of a known reflectance tile which was kept constantly within the field of view for all image scans. A method to split images containing rows of multiple raspberry plants into individual plants was also developed. Validation was carried out by comparison of plant height and density measurements with manually scored values. A reasonable correlation was found between these manual scores and measurements taken from the images (r2 = 0.75 for plant height). These preliminary steps are an essential requirement before detailed spectral analysis of the plants can be achieved.

Using Unmanned Aircraft Systems for Early Detection of Soybean Diseases

As the interest in Unmanned Aerial Systems (UAS) has increased, so has the interest in the application of these systems for use in agriculture. A variety of sensors, including Multi-Spectral, Near-Infrared, Thermal, and True-Color have the potential to benefit farmers when mounted to a UAS. But as this is an emerging field, there is little data available to demonstrate their use for early detection of plant diseases in crop production. In 2016, a preliminary study was launched to examine the potential of using aerial imagery from UAS to detect diseases in soybean crops. Two irrigated fields in Alabama were selected: Experiment 1, a 50-hectare field, and Experiment 2, a 5-hectare field. Each trial consisted of replicated plots using two foliar fungicide treatments and an untreated control. Aerial imagery (multi-spectral and true-color) was collected on a biweekly basis during this study. Using multi-spectral imagery, both the Normalized Difference Vegetative Index (NDVI) and Normalized Difference Red Edge Index (NDRE) were generated and compared to direct observations in the field. Disease severity of soybean rust, charcoal rot and Cercospora leaf blight were monitored on a biweekly basis and correlated to the UAS imagery. Preliminary results indicated plant stress can be detected using UAS imagery. In Experiment 1, stress associated with charcoal rot was visible in the NDRE imagery. This was of interest because at the time of flight, while it was noted that plants were yellowing, the root and stem disease itself had not been identified by direct observation. In Experiment 2, soybean rust was observed by direct observation and in both the NDRE and NDVI imagery. Soybean rust did have a negative impact on yield in Experiment 2, however severe drought conditions may have negated the yield loss likely caused by the development of charcoal rot in Experiment 1.

Review of Leaf Unhealthy Region Detection Using Image Processing Techniques

Abstract- In agricultural field the plants comes to an attack from the various pets bacterial and micro-organism diseases. This diseases attacks on the plant leaves, steams, and fruit part. This present review paper discussed the image processing techniques which is used in performing the early detection of plant diseases through leaf feature inspection. the basic objective of this work is to develop image analysis and classification techniques for extraction and finally classified the diseases present on leaf. Image of leaf is captured and the process is performed and to determine the status of each plant. Here proposed model divide into four parts. The image preprocessing including normalization and contrast adjustment; segment the region of interest determine by using color transform YCbCr and bi-level thresholding for statistical usage to determine the defect and severity area of plant leaves. The texture feature extraction using statistical GLCM (Gray Level Co-occurrences Matrix) and color feature by means values.[1] Finally classification achieved using random markov model.

Characterizing canopy structural complexity for the estimation of maize LAI based on ALS data and UAV stereo images

ABSTRACTThe canopy structure of crops is a fundamental attribute of agro-ecosystems, providing efficient indications of the growing status, water stress, early detection of plant diseases, and yield estimation. In this study, we investigated the potential of point clouds generated from airborne laser scanning (ALS) and stereo images from an unmanned aerial vehicle (UAV) to characterize the structural complexity of maize canopies. The simultaneous collection of point clouds and field measurements were conducted on three sampling dates. A group of metrics that are often used in forest studies was calculated to quantify the structural complexity of canopies, which was further used to estimate the leaf area index (LAI) of maize. Stepwise linear regression models were established based on the metrics and LAI using the data sampled at single and mixed sampling dates, respectively. Results showed that significantly high correlations were found between the LAI values of maize and complexity metrics with a Pearson correlation coefficient (r) greater than 0.60. The leave one-out cross-validation (LOOCV) of LAI estimation showed that the highest robustness (RMSE = 0.16, rRMSE = 5.63%) was obtained by the model that was established from the overall data set, which explained 75% of the variation in the field-measured LAI. To conclude, the metrics of canopy structural complexity can be powerful predictors in the estimation of maize LAI based on our data set, which provides some new ideas for the study of precision agriculture using remote sensing.

Biosensors for plant pathogen detection

Infectious plant diseases are caused by pathogenic microorganisms such as fungi, bacteria, viruses, viroids, phytoplasma and nematodes. Worldwide, plant pathogen infections are among main factors limiting crop productivity and increasing economic losses. Plant pathogen detection is important as first step to manage a plant disease in greenhouses, field conditions and at the country boarders. Current immunological techniques used to detect pathogens in plant include enzyme-linked immunosorbent assays (ELISA) and direct tissue blot immunoassays (DTBIA). DNA-based techniques such as polymerase chain reaction (PCR), real time PCR (RT-PCR) and dot blot hybridization have also been proposed for pathogen identification and detection. However these methodologies are time-consuming and require complex instruments, being not suitable for in-situ analysis. Consequently, there is strong interest for developing new biosensing systems for early detection of plant diseases with high sensitivity and specificity at the point-of-care. In this context, we revise here the recent advancement in the development of advantageous biosensing systems for plant pathogen detection based on both antibody and DNA receptors. The use of different nanomaterials such as nanochannels and metallic nanoparticles for the development of innovative and sensitive biosensing systems for the detection of pathogens (i.e. bacteria and viruses) at the point-of-care is also shown. Plastic and paper-based platforms have been used for this purpose, offering cheap and easy-to-use really integrated sensing systems for rapid on-site detection. Beside devices developed at research and development level a brief revision of commercially available kits is also included in this review.

Automated Plant Viability System for Early Detection of Plant Disease

Abstract: This paper reports on the design and implementation of a plant viability sensor system based on micro fabrication and wireless communication technologies. The system consists of a Solid Phase Micro-extraction (SPME) Injector, a gas chromatography column with OV-1 coating, a low power thermal conductivity sensor, and a circuit design. The system uses the SPME injection method which allows injection of small amounts of analytes into the GC system instantly. The column with a 2 dimensional temperature programming provides a better separation of the volatile compounds and the CMOS TCD sensors provides high resolution for detection of a low concentration. A 12 bit microcontroller with a low noise circuit system and a Bluetooth communication technology are implemented for live monitoring of the VOC gases. The documented performance shows that the system is able to detect and transmit the volatile organic compounds of interest to a handheld device.

Handheld Raman spectroscopy for the early detection of plant diseases: Abutilon mosaic virus infecting Abutilon sp.

Plant diseases have a direct impact on the productivity of crops, and therefore the early detection of diseases is crucial.