Bacterial Spot Research Articles

Draft genome sequences of 11 Xanthomonas strains associated with bacterial spot disease in Turkey.

Bacterial spot is an economically significant disease in tomato and pepper-producing countries globally. We report the whole-genome sequence of 11 Xanthomonas strains associated with bacterial spot disease on pepper, tomato and eggplant in the Southeastern Anatolia Region, Turkey. This genomic information can be used as a reference to study the genetic diversity of these species and contribute to illuminating pathogen evolution with respect to host specificity.

Utilization of a New Hundred-Genomes Pipeline to Design a Rapid Duplex LAMP Detection Assay for Xanthomas euvesicatoria and X. vesicatoria in Tomato.

Xanthomonas euvesicatoria (Xe) and X. vesicatoria (Xv) are two economically important causal agents of bacterial spot (BS) of tomato and pepper. Management of BS in the field requires rapid and accurate detection. This work therefore aimed to develop a pipeline to design a simple, fast, and reliable assay for the detection of Xe and Xv by Loop-Mediated Isothermal Amplification (LAMP). A total of 109 publicly available whole genomic sequences of 24 different species of bacterial pathogens were used to design primers that would amplify the DNA of the two target species. Laboratory testing of the assay was performed on pure bacterial cultures and artificially infected plants, and amplification was conducted with both a sophisticated laboratory instrument and a simple mobile platform. The testing of the assay confirmed its specificity with a sensitivity reaching 1 pg μL-1 for both pathogens with an assay duration of 40 minutes on a mobile detection platform. Our diagnostics development pipeline enables the easy and fast design of a reliable detection assay in the genomics age. By validating the pipeline with Xe and Xv pathogens, we have simultaneously developed an assay with high specificity, sensitivity, and speed, which will allow it to be deployed, contributing to successful management of BS.

Multiclass Classification of Paddy Leaf Diseases Using Random Forest Classifier

With increase in population, improving the quality and quantity of food is essential. Paddy is a vital food crop serving numerous people in various continents of the world. The yield of paddy is affected by numerous factors. Early diagnosis of disease is needed to prevent the plants from successive stage of disease. Manual diagnosis by naked eye is the traditional method widely adopted by farmers to identify leaf diseases. However, when the task involves manual disease diagnosis, problems like the hiring of domain experts, time consumption, and inaccurate results will arise. Inconsistent results may lead to improper treatment of plants. To overcome this problem, automatic disease diagnosis is proposed by researchers. This will help the farmers to accurately diagnose the disease swiftly without the need for expert. This manuscript develops model to classify four types of paddy leaf diseases bacterial blight, blast, tungro and brown spot. To begin with, the image is preprocessed by resizing and conversion to RGB Red, Green and Blue (RGB) and Hue, Saturation and Value (HSV) color space. Segmentation is done. Global features namely: hu moments, Haralick and color histogram are extracted and concatenated. Data is split in to training part and testing part in 70:30 ratios. Images are trained using multiple classifiers like Logistic Regression, Random Forest Classifier, Decision Tree Classifier, K-Nearest Neighbor (KNN) Classifier, Linear Discriminant Analysis (LDA),Support Vector Machine (SVM) and Gaussian Naive Bayes. This study reports Random Forest classifier as the best classifier. The Accuracy of the proposed model gained 92.84% after validation and 97.62% after testing using paddy disordered samples. 10 fold cross validation is performed. Performance of classification algorithms is measured using confusion matrix with precision, recall, F1- score and support as parameters.

Chili Leaf Disease Prediction Using CNN

Abstract: Chili leaf diseases cause significant damage to chili plants, leading to reduced crop yield and economic losses for farmers. Early detection and diagnosis of these diseases are crucial for effective disease management. In this research paper, we propose a chili leaf disease prediction model using Convolutional Neural Network (CNN). The proposed model utilizes an image dataset collected from different regions ,consisting of chili leaf images infected with common chili leaf diseases, like bacterial leaf spot, leaf Curl , Mosaic virus, etc. We pre-processed the dataset to enhance the image quality and to remove noise. The preprocessed dataset was split into training and validation sets. The CNN model was trained using the training set and validated using the validation set. The proposed model achieved an high accuracy on the validation set. The proposed model can be used to predict the occurrence of chili leaf diseases in real-time, which can help farmers in taking preventive measures to protect their crops

Leaf Disease Detection in Android

Abstract: In agriculture, early disease identification is crucial for a productive crop product. Ails similar as bacterial spot, late scar, Septoria splint spot, and unheroic twisted splint the quality of the tomato crop. Automatic bracket ways of factory conditions also help in taking action once they're discovered diseased splint symptoms Presented below is a Convolutional Learning Vector Quantization and Neural Network( CNN) model system for detecting tomato splint dis- ease grounded on the( LVQ) algorithm and categorization. There are 500 tomato prints in the dataset. leaves that display four complaint symptoms. We created a model of CNN for point birth and categorization automatically. Color Research on factory splint conditions laboriously uses information. In our model, three channels grounded on RGB are subordinated to pollutants

Leaf Disease Detection

Abstract: Early disease identification is crucial for productive crop production in agriculture. illnesses such as bacterial spot, late blight, Septoria leaf spot, and yellow curved leaf the quality of the tomato harvest. Automatic classification techniques of plant diseases also assist in taking action once they are discovered diseased leaf symptoms Presented below is a Convolutional Learning Vector Quantization and Neural Network (CNN) model Method for detecting tomato leaf disease based on the (LVQ) algorithm and categorization. There are 500 tomato photos in the dataset. leaves that display four disease symptoms. We created a model of CNN for feature extraction and categorization automatically. Color Research on plant leaf diseases actively uses information. In our model, three channels based on RGB are subjected to filters.

Xanthomonas euvesicatoria pv. perforans is the causative agent of bacterial leaf spot on Ipomoea aquatica from Fujian Province in China

Xanthomonas euvesicatoria pv. perforans is the causative agent of bacterial leaf spot on Ipomoea aquatica from Fujian Province in China

Mapping of the bs5 and bs6 non-race-specific recessive resistances against bacterial spot of pepper.

Bacterial spot caused by Xanthomonas euvesicatoria is a major disease of pepper (Capsicum annuum L.) in warm and humid production environments. Use of genetically resistant cultivars is an effective approach to manage bacterial spot. Two recessive resistance genes, bs5 and bs6, confer non-race-specific resistance against bacterial spot. The objective of our study was to map these two loci in the pepper genome. We used a genotyping-by-sequencing approach to initially map the position of the two resistances. Segregating populations for bs5 and bs6 were developed by crossing susceptible Early CalWonder (ECW) with near-isogenic lines ECW50R (bs5 introgression) or ECW60R (bs6 introgression). Following fine-mapping, bs5 was delimited to a ~535 Kbp interval on chromosome 3, and bs6 to a ~666 Kbp interval in chromosome 6. We identified 14 and 8 candidate resistance genes for bs5 and bs6, respectively, based on predicted protein coding polymorphisms between ECW and the corresponding resistant parent. This research enhances marker-assisted selection of bs5 and bs6 in breeding programs and is a crucial step towards elucidating the molecular mechanisms underlying the resistances.

On-farm Validation of Coffea arabica and Aloe vera Extracts for Management of Seed-Borne Bacterial Leaf Spot Disease of Tomato

On-farm Validation of Coffea arabica and Aloe vera Extracts for Management of Seed-Borne Bacterial Leaf Spot Disease of Tomato

First Report of the Occurrence of the Bacterial Spot Disease of Stone Fruits Caused by Xanthomonas arboricola pv. pruni on Almond in Greece.

In 2021, two samples of almond (Prunus dulcis (Mill) Webb) shoots with symptoms resembling those caused by Xanthomonas arboricola pv. pruni (Xap), were examined at the Benaki Phytopathological Institute. The first sample was collected in June from a 0.4-ha orchard of fifteen-year-old almond trees (cv. 'Texas') with 40% disease incidence, in the Regional Unit of Serres (Northern Greece). Leaves exhibited, mainly at their tip and margins, small, angular, necrotic spots with chlorotic halo, often coalesced into larger necrotic lesions which fell out leaving leaves with a 'shot-hole' like appearance. Fruits displayed dark brown, sunken, corky, gum oozing lesions and shoots developed dark brown, elongated, slightly sunken lesions. Bacterial streaming from the marginal areas of necrotic lesions was observed microscopically. On the lesions of fruits, leaves and shoots, Xap was detected by immunofluorescence assay (IF) using polyclonal antibodies (Plant Research International, the Netherlands) and two qPCR assays (Garita-Cambronero et al. 2017; Palacio-Bielsa et al. 2011). Eight Xanthomonas-like isolates obtained on the SP agar (Hayward 1960) and Nutrient agar (Schaad et al. 2001) culture media were Gram-negative, oxidase negative, strictly aerobic, sensitive to 0.1% w/v TTC, hydrolysing gelatin and Tween 80 but not starch, and also inducing hypersensitive response in tomato plants, as expected for Xap (Schaad et al. 2001). Isolates' identification was confirmed by the IF and the two qPCR assays cited above, as well as a conventional PCR (Pothier et al., 2011). Infiltration of a suspension (107 cfu/ml) of one isolate into five leaves of a two-year-old almond tree cv. 'Texas', and also into five detached leaves from the same tree (Randhawa and Civerolo 1985), caused necrotic spots on all inoculated leaves (10 inoculation sites/leaf), after a four day incubation period at 25oC under high humidity. The Xap reference strain NCPPB 3877 and sterile water were used as positive and negative controls, respectively. The pathogen was reisolated from necrotic spots of the inoculated leaves and identified by IF and two qPCR assays, as previously. The second sample was collected by a grower in September from a 3.7-ha orchard of five-year-old almond trees (cv. 'Tuono') exhibiting 50% disease incidence, in the Regional Unit of Fthiotida (Central Greece). Leaves and fruits showed symptoms similar to those described for the first sample, except that, lesions on fruits, which were at a stage of advanced mesocarp dehydration, were raised. Five Xap isolates were obtained from symptomatic leaves and fruits, and their pathogenicity on almond was confirmed, as in the first sample. Furthermore, sequences of PCR products using primers targeting the 16S-rDNA (Lane 1991;Lane et al., 1985), gyrB (Parkinson et al. 2007) and ftsX (Pothier et al. 2011) genes of two Xap isolates, one from fruit- and one from leaf-necrotic lesions of the first sample, were searched against the NCBI GenBank database, revealing that the obtained sequences of 16S-rRNA (OP412487; OP412488), gyrB (OP467593; OP467594) and ftsX (OP467595; OP467596) genes were 100% identical to the corresponding genomic regions of the Xap strains IVIA 2626.1 (CP076628.1) and CITA 33 (CP076701.1). This is the first report on the presence of Xap in Greece. As these Xap outbreaks have occurred in regions with extensive almond cultivation, a crop of great economic importance for Greece, measures for its eradication have already been advised.

Marker-assisted Selection to Combine Alleles for Four Disease Resistance Genes of Tomato Collocated on Chromosome 11

Bacterial, fungal, and viral diseases of tomato (Solanum lycopersicum) are responsible for widespread yield losses, especially in humid growing environments. Chromosome 11 of tomato contains genes that modulate resistance to several prominent tomato pathogens, including bacterial spot caused by Xanthomonas spp., gray leaf spot caused by Stemphylium spp., Fusarium wilt caused by race 2 of Fusarium oxysporum f. sp. lycopersici, and tomato yellow leaf curl virus (TYLCV) caused by begomoviruses. Major resistance loci are quantitative trait locus 11 (QTL-11) and Xv3/Rx4 for bacterial spot, Sm for gray leaf spot, I2 for Fusarium wilt, and Ty-2 for TYLCV. Marker-assisted selection was used to select for rare recombination events that combined these resistance loci into a linked cassette that can be inherited together in future crosses. A pedigree breeding strategy was used with marker-assisted selection and used to identify a novel coupling of Xv3/Rx4 and Ty-2. Recombination between the two genes was estimated as 0.056 cM, demonstrating that effective combinations of resistance can be established using publicly available germplasm. Progeny from the recombinant plants were screened using inoculated seedling trials to confirm resistance. The recombinants identified maintained resistance levels similar to the resistant controls. Trial results suggest that the trait markers on chromosome 11 are tightly linked to the respective resistance loci and are effective for selecting plants with resistance to the target diseases.

Moringa olefra Plant Based Copper and Silver Nano Particles and its Antibacterial Activity towards Leaf Spot of Chilli caused by Xanthomonas campestris pv. vesicatoria

Bacterial leaf spot caused by Xanthomonas campestris pv. vesicatoria (Xcv) is one of the most devastating diseases, causing serious losses in chilli crop yield. The extensive usage of chemicals has increased the toxicity of the environment. Nanotechnology products are indeed being developed as a promising approach for plant disease control with minimal impact on the environment. In the present research, the antibacterial activity of green synthesized nanoparticles (Silver and Zinc nanoparticles) was investigated against Xcv. Different concentrations (0.25, 0.6 and 0.75%) of the green synthesized nanoparticles (AgNPs and ZnNPs) along with their combination were evaluated under lab conditions against Xcv under Complete Randomized Design (CRD). Results showed that the combination of both nanoparticles (AgNPs+ZnNPs) gave the best results and expressed maximum inhibition zone (25.207 mm), followed by solo applications of AgNPs and ZnNPs (18.458 and 12.253 mm). Whereas, the interaction of treatment and concentration combination (AgNPs+ZnNPs) expressed a maximum inhibition zone (28.459 mm) at 0.75% concentration as compared to other treatments. The concentration (0.75%) at which bacteria showed the maximum inhibition zone was used to control the bacterial leaf spot of chilli under field conditions. The experiment was conducted under a Completely Randomized Block Design (RCBD) where AgNPs+ZnNPs expressed the best results with minimum disease incidence (21.92%) followed by solo treatments of AgNPs and ZnNPs (26.999 and 35.320%)

Exploring the Potential of Green Silver Nanoparticles from Berberis vulgaris against Bacterial Spot of Tomato and its Surveillance in Poonch District

Bacterial spot of tomato is a major constraint to tomato production in tropical, subtropical, and temperate climates, leading to significant crop losses. The current study aimed to manage the highly devastating disease bacterial spot of tomato, caused by Xanthomonas perforans, using green silver nanoparticles based on Berberis vulgaris plant extract. Disease parameters, namely disease prevalence and disease incidence, were calculated from tomato growing areas of district Poonch, AJK, to document the current status of bacterial spot disease on local tomato cultivars. The associated pathogenic strains were purified, and virulence study was conducted on healthy tomato seedlings followed by characterization using morphological, biochemical, and molecular analysis. B. vulgaris plant extract was used for the preparation of green silver nanoparticles (AgNPs), and three different concentrations were prepared (0.2%, 0.4%, and 0.6%). For texture and molecular composition study, characterization of green AgNPs was done using Fourier-transform infrared spectroscopy (FTIR) and scanning electron microscopy (SEM). Green silver nanoparticles were then evaluated using the inhibition zone technique in the lab, and it was found that the maximum inhibition zone of 24.32 mm was observed at a 0.6% concentration. Similarly, in the greenhouse experiment, the minimum disease incidence was recorded in the treatment with a 0.6% concentration of green AgNPs. The results of the current study showed a significant reduction in disease incidence while using green silver nanoparticles against bacterial spot of tomato

Greenhouse-Grown Tomatoes: Microbial Diseases and their Control Methods: A Review

The cultivation of tomatoes in greenhouse structures is becoming increasingly common as a crop production system. However, the environmental conditions inside a greenhouse favour the development of microbial diseases. These diseases have an adverse effect on the tomato yield and can lead to serious economic losses. This review will give an insight into the major diseases affecting greenhouse-grown tomatoes, the respective causal agents and recommended control strategies. Some of the major diseases are of a bacterial, fungal, viral or nematode origin and include bacterial spot and speck, bacterial canker, early blight, gray mold, leaf mold, powdery mildew, tomato mosaic virus, tomato big bug and root knot. For each disease, the symptoms and risk factors responsible for disease development are described. In addition, the different structural designs and set-ups of tomato greenhouses are covered along with their advantages and limitations, especially any adverse effects on yield and susceptibility to disease. Although conventional control measures are discussed, greater emphasis is laid on the use of alternative biocontrol measures that include Effective Microorganisms, natural antimicrobials and nanobiopesticides. Moreover, information gathered in this review is based on a combination of available literature and expert guidance. This compilation is hoped to be instructive for tomato growers opting for greenhouse farming and assist them in the application of timely and more effective control measures

Potential of Novel Magnesium Nanomaterials to Manage Bacterial Spot Disease of Tomato in Greenhouse and Field Conditions.

Bacterial spot of tomato is among the most economically relevant diseases affecting tomato plants globally. In previous studies, non-formulated magnesium oxide nanoparticles (nano-MgOs) significantly reduced the disease severity in greenhouse and field conditions. However, the aggregation of nano-MgO in liquid suspension makes it challenging to use in field applications. Therefore, we formulated two novel MgO nanomaterials (SgMg #3 and SgMg #2.5) and one MgOH2 nanomaterial (SgMc) and evaluated their physical characteristics, antibacterial properties, and disease reduction abilities. Among the three Mg nanomaterials, SgMc showed the highest efficacy against copper-tolerant strains of Xanthomonas perforans in vitro, and provided disease reduction in the greenhouse experiments compared with commercial Cu bactericide and an untreated control. However, SgMc was not consistently effective in field conditions. To determine the cause of its inconsistent efficacy in different environments, we monitored particle size, zeta potential, morphology, and crystallinity for all three formulated materials and nano-MgOs. The MgO particle size was determined by the scanning electron microscopy (SEM) and dynamic light scattering (DLS) techniques. An X-ray diffraction (XRD) study confirmed a change in the crystallinity of MgO from a periclase to an Mg(OH)2 brucite crystal structure. As a result, the bactericidal activity correlated with the high crystallinity present in nano-MgOs and SgMc, while the inconsistent antimicrobial potency of SgMg #3 and SgMg #2.5 might have been related to loss of crystallinity. Future studies are needed to determine which specific variables impair the performance of these nanomaterials in the field compared to under greenhouse conditions. Although SgMc did not lead to significant disease severity reduction in the field, it still has the potential to act as an alternative to Cu against bacterial spot disease in tomato transplant production.

Bio-fabrication of zinc oxide nanoparticles from Picea smithiana and their potential antimicrobial activities against Xanthomonas campestris pv. Vesicatoria and Ralstonia solanacearum causing bacterial leaf spot and bacterial wilt in tomato.

Due to an inevitable disadvantage of chemical or physical synthesis routes, biosynthesis approach to nanoparticles, especially metallic oxide is attractive nowadays. Metallic oxides nanoparticles present a new approach to the control of plant pathogens. ZnO nanoparticles (ZNPs) have very important role in phytopathology. In current study, biosynthesized ZNPs were tested against two devastating bacterial pathogens including Xanthomonas campestris pv. vesicatoria and Ralstonia solanacearum causing bacterial leaf spot and bacterial wilt in tomato. ZNPs were produced using a new extract from the plant Picea smithiana using an environmentally friendly, cost-effective and simple procedure. Zinc acetate was added to P. smithiana extract, stirred and heated to 200°C. The white precipitation at the bottom were clear indication of synthesis of nanoparticles, which were further dried by subjecting them at 450°C. X-ray diffraction pattern determined that the ZNPs had a crystallite size of about 26nm, Fourier transform infrared spectroscopy indicated a peak between 450 and 550cm-1 and the particle size estimated by dynamic light scattering was about 25nm on average. Scanning electron microscopic analysis indicated that the particles were hexagonal in shape 31nm in diameter. Antibacterial tests showed ZNPs synthesized by P. smithiana resulted in clear inhibition zones of 20.1 ± 1.5 and 18.9 ± 1.5mm and 44.74 and 45.63% reduction in disease severity and 78.40 and 80.91% reduction in disease incidence in X. compestris pv. vesicatoria and R. solanacearum respectively at concentration of 100µg/ml. Our findings reveal that the concentration of ZNPs was important for their efficient antibacterial activity. Overall, the biosynthesized ZNPs have been found to have effective antimicrobial activities against bacterial wilt and bacterial leaf spot in tomato.

Pre-Trained Deep Neural Network-Based Features Selection Supported Machine Learning for Rice Leaf Disease Classification

Rice is a staple food for roughly half of the world’s population. Some farmers prefer rice cultivation to other crops because rice can thrive in a wide range of environments. Several studies have found that about 70% of India’s population relies on agriculture in some way and that agribusiness accounts for about 17% of India’s GDP. In India, rice is one of the most important crops, but it is vulnerable to a number of diseases throughout the growing process. Farmers’ manual identification of these diseases is highly inaccurate due to their lack of medical expertise. Recent advances in deep learning models show that automatic image recognition systems can be extremely useful in such situations. In this paper, we propose a suitable and effective system for predicting diseases in rice leaves using a number of different deep learning techniques. Images of rice leaf diseases were gathered and processed to fulfil the algorithmic requirements. Initially, features were extracted by using 32 pre-trained models, and then we classified the images of rice leaf diseases such as bacterial blight, blast, and brown spot with numerous machine learning and ensemble learning classifiers and compared the results. The proposed procedure works better than other methods that are currently used. It achieves 90–91% identification accuracy and other performance parameters such as precision, Recall Rate, F1-score, Matthews Coefficient, and Kappa Statistics on a normal data set. Even after the segmentation process, the value reaches 93–94% for model EfficientNetV2B3 with ET and HGB classifiers. The proposed model efficiently recognises rice leaf diseases with an accuracy of 94%. The experimental results show that the proposed procedure is valid and effective for identifying rice diseases.

Differential responses in some quinoa genotypes of a consortium of beneficial endophytic bacteria against bacterial leaf spot disease.

Many effective plant-microbe interactions lead to biological changes that can stimulate plant growth and production. This study evaluated the effect of the interaction between quinoa (Chenopodium quinoa Willd.) and endophytic bacterial strains on differential responses under biotic stress. Four strains of endophytic bacteria were used to inoculate three quinoa genotypes. Endophytic bacteria, isolated from the endosphere of healthy genotypes of quinoa plants, were used to evaluate their biocontrol activity against Pseudomonas syringae on quinoa plants, which causes leaf spot disease, depending on some different parameters. Quinoa genotype plants were treated with four treatments: pathogenic bacteria only (T1), internal bacteria only (T2), pathogenic bacteria + endogenous bacteria (T3), and untreated as the control (T4). The results indicated that there was a significant difference between chlorophyll content index of infected plants without bioagent (untreated) compared to plants bio-inoculated with endophytic bacteria. The highest mean disease incidence was on the plants without bacterial inoculum (90, 80, and 100%) for quinoa genotypes G1, G2, and G3, respectively. The results showed that there were significant differences in the weight of grains/plant, as the value ranged from 8.1 to 13.3 g when treated with pathogens (T1) compared to the treatment with pathogens and endogenous bacteria (T3), which ranged from 11.7 to 18.6 g/plant. Decreases in total aromatic amino acids appeared due to the pathogen infection, by 6.3, 22.8, and 24.1% (compared to the control) in G1, G2, and G3, respectively. On the other hand, genotype G3 showed the highest response in the levels of total aromatic and total neutral amino acids. The endophytic strains promoted quinoa seedling growth mainly by improving nutrient efficiency. This improvement could not be explained by their ability to induce the production of amino acids, showing that complex interactions might be associated with enhancement of quinoa seedling performance by endophytic bacteria. The endophytic bacterial strains were able to reduce the severity of bacterial leaf spot disease by 30, 40, and 50% in quinoa genotypes G1, G2, and G3, respectively, recording significant differences compared to the negative control. The results indicated that, G1 genotype was superior in different performance indicators (pathogen tolerance index, yield injury %, superiority measure and relative performance) for grain weight/plant under pathogen infection condition when treated with endophyte bacteria. Based on this study, these bacterial strains can be used as a biotechnology tool in quinoa seedling production and biocontrol to diminish the severity of bacterial leaf spot disease.

Early Detection of Plant Leaf Disease Using Deep Learning

As crop diseases spread, farmers need to prevent and control their contamination to increase productivity and yield. In addition to affecting plants, plant diseases affect market access and agricultural production. As one of the most important vegetable plants in the world, leaf images can be used to classify diseases early. In addition to Yellow Curved, Late Blight, and Leaf Spot, Bacterial leaf Spot, there are other diseases of plants. The dataset is taken from the Internet. In this paper, we take leaf images with various leaf diseases and train it with the best model Convolutional Neural Network (CNN). We then use the weights from CNN to test new leaf images. By using convolutional neural networks (CNNs) and deep learning techniques, we have proposed a system that classifies plant leaf diseases. With the hybrid approach, the model will demonstrate its accuracy. To identify the best model, performance analysis is done with accuracy and finds solution to the problem.

Impact of Data Augmentation Techniques on the Implementation of a Combination Model of Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) for the Detection of Diseases in Rice Plants

Detection of disease in rice plants is important to avoid damage and reduce yields. In this study, the influence of data augmentation techniques on the application of a combination model of Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) was carried out to detect diseases in rice plants. This study uses a dataset of rice images for disease detection which contains 6034 images of rice with five categories, namely Bacterial Leaf Bligh, Blast, Brown Spot, normal, and tungro. This dataset is divided into three parts, namely training data, validation data and test data. The data augmentation techniques used are rotation, brightness and zoom on rice images. The combination model of CNN and MLP is built using the Python programming language and the TensorFlow deep learning framework. In measuring the success rate of the built model, it can be measured using the accuracy, precision and recall values obtained in the model test. Several scenarios were carried out to produce the best model, namely the use of data augmentation techniques, the number of layers and the number of iterations (epochs). From the experiments that have been carried out which have been tested with data as many as 25 digital images, the best model is obtained with an testing accuracy of 92%, 94% precision and 92% recall. This model applies a random zoom augmentation technique with a value of 0.5 – 1.0, CNN+MLP with 3 layers and a dataset ratio of 80:20 and an epoch early stop, This result has increased by more than 10%.