Tomato Spotted Wilt Disease Severity Levels Detection: A Deep Learning Methodology
TL;DR: In this paper, a deep learning-based convolutional neural networks (CNN) model has been presented to detect and classify tomato spotted wilt (TSW) disease in real-time and self-captured images.
Abstract: The wide variety of diseases in the tomato plant affects the quality and quantity of the production. To counteract the problem of disease in tomato plants deep learning (DL) based convolutional neural networks (CNN) model has been presented in this paper that classify the real-time and self-captured 3000 images of healthy and tomato spotted wilt (TSW) disease plants. TSW is a type of infected virus that turns the upper sides of young tomato leaves as bronze and eventually acquires prominent, necrotic spots. Binary and multi-classification of the collected dataset have been made based on three different types of severity levels of TSW disease. In the case of binary classification, the accuracy is recorded at 91.56% and on the other hand, the best accuracy of multi-classification is recorded at 95.23% in the case of middle severity level. The model shows the least accuracy 94.5% and middle accuracy 95.2% in the case of early-stage severity and late severity level respectively. The proposed work will make a significant addition to the field of employing DL techniques to detect and classify tomato diseases.
Citations
More filters
28 Apr 2022
TL;DR: This work cogitates three paddy leaf diseases for the creation of an AI-based robust detection and classification model using a novel approach to the convolutional neural network with the combination of augmentation and a CNN model tuner.
Abstract: A variety of fungal and bacterial leaf ailments wreak havoc on the paddy plant in the agricultural field. Early diagnosis of leaf infection can improve the yield of the crop. The modeling of an automatic disease classifier aids farmers in handling the spread of leaf disease in the agricultural field. This work cogitates three paddy leaf diseases (Bacterial blight, leaf smut, and leaf blast) for the creation of an AI-based robust detection and classification model. The dataset is collected from a variety of standard online repositories. GAN-based augmentation technique was used for increasing the size of the dataset. A novel approach to the convolutional neural network is proposed with the combination of augmentation and a CNN model tuner. The performance of CNN is evaluated in terms of accuracy achieved is 98.23\% in the classification process.
24 citations
TL;DR: In this article , a hybrid prediction model was developed to predict various levels of severity of blast disease based on diseased plant images, which achieved 97% accuracy with the help of CNN and SVM.
Abstract: Hypothesis: Due to the increase in the losses in paddy yield as a result of various paddy diseases, researchers are working tirelessly for a technological solution to assist farmers in making decisions about disease severity and potential danger to the crop. Early prediction of infection severity would facilitate resources for the treatment of the infection and prevent contamination to the whole field. Methodology: In this study, a hybrid prediction model was developed to predict various levels of severity of blast disease based on diseased plant images. The proposed model is a four-fold severity prediction model. The level of severity is defined based on the percentage of leaf area affected by the disease. The image dataset is derived from both primary and secondary resources. Tools: The features are first extracted with the help of the Convolutional Neural Network (CNN) approach. Then the identification and classification of the severity level of blast disease are conducted using a Support Vector Machine (SVM). Conclusion: Mendeley, Kaggle, GitHub, and UCI are the secondary resources used for dataset generation. The number of images in the dataset is 1908. The proposed hybrid model achieves 97% accuracy.
18 citations
TL;DR: In this paper , a novel neural network-based hybrid model (GCL) is introduced, which is a dataset-augmentation fusion of long short term memory (LSTM) and convolutional neural network (CNN) with generative adversarial network (GAN).
Abstract: The demand for agricultural products increased exponentially as the global population grew. The rapid development of computer vision-based artificial intelligence and deep learning-related technologies has impacted a wide range of industries, including disease detection and classification. This paper introduces a novel neural network-based hybrid model (GCL). GCL is a dataset-augmentation fusion of long-short term memory (LSTM) and convolutional neural network (CNN) with generative adversarial network (GAN). GAN is used for the augmentation of the dataset, CNN extracts the features and LSTM classifies the various paddy diseases. The GCL model is being investigated to improve the classification model’s accuracy and reliability. The dataset was compiled using secondary resources such as Mendeley, Kaggle, UCI, and GitHub, having images of bacterial blight, leaf smut, and rice blast. The experimental setup for proving the efficacy of the GCL model demonstrates that the GCL is suitable for disease classification and works with 97% testing accuracy. GCL can further be used for the classification of more diseases of paddy.
11 citations
02 Feb 2023
TL;DR: In this paper , the authors used CNN and SVM for feature extraction and classification of the various levels of severity of sugarcane smut infection, and the best features of the deep learning techniques were applied.
Abstract: Traditional models for predicting diseases in sugarcane crops show some drawbacks, including expensive costs for getting the data input needed to execute the model, a lack of spatial data, or a poor dataset. These problems are discussed in this work, which also develops a yield prediction fusion model. Convolutional neural networks (CNN) and support vector machines (SVM). make up the prediction model.In this work, the leaf smut infection of sugarcane is discussed. The sick plant is first photographed utilizing secondary sources. For feature extraction and classification of the various levels of severity of the smut infection, the best features of the deep learning techniques CNN and SVM are applied. Mild, Average, Severe, and Profound are the four seriousness prediction levels used in the study. Mendeley and Kaggle are the data repositories that were utilized, and the total size of the dataset was 950. The four severity level forecasts made by the suggested framework are 98% accurate.
4 citations
28 Apr 2022
TL;DR: This paper will first explain Python as a language, then introduce Data Science, Machine learning, and IOT, describing prominent packages in the Data Science and Machine learning community, such as NumPy, SciPy, TensorFlow, Keras, Matplotlib.
Abstract: Python is an object-oriented, scripting, and interpretive programming language that may be used for mentoring and real-world applications. This paper focusses primarily on Python software packages used in data science, pattern recognition, and IoT. This paper will first explain Python as a language, then introduce Data Science, Machine learning, and IOT, describing prominent packages in the Data Science and Machine learning community, such as NumPy, SciPy, TensorFlow, Keras, Matplotlib. This paper will also demonstrate the significance of Python in the development of the industry. Throughout, we shall utilize many code samples. We review so many research papers to analyze the usage of python in different fields and easily import packages in the programming software.
2 citations
References
More filters
01 Jan 2014
TL;DR: A customized Convolutional Neural Networks with shallow convolution layer to classify lung image patches with interstitial lung disease and the same architecture can be generalized to perform other medical image or texture classification tasks.
Abstract: Image patch classification is an important task in many different medical imaging applications. In this work, we have designed a customized Convolutional Neural Networks (CNN) with shallow convolution layer to classify lung image patches with interstitial lung disease (ILD). While many feature descriptors have been proposed over the past years, they can be quite complicated and domain-specific. Our customized CNN framework can, on the other hand, automatically and efficiently learn the intrinsic image features from lung image patches that are most suitable for the classification purpose. The same architecture can be generalized to perform other medical image or texture classification tasks.
551 citations
TL;DR: Although SVM outperformed the ANN classifiers with regard to overall prediction accuracy, both methods were shown to complement each other, as the sets of true positives, false positives, true negatives, and false negatives produced by the two classifiers were not identical.
Abstract: Support vector machine (SVM) and artificial neural network (ANN) systems were applied to a drug/nondrug classification problem as an example of binary decision problems in early-phase virtual compound filtering and screening. The results indicate that solutions obtained by SVM training seem to be more robust with a smaller standard error compared to ANN training. Generally, the SVM classifier yielded slightly higher prediction accuracy than ANN, irrespective of the type of descriptors used for molecule encoding, the size of the training data sets, and the algorithm employed for neural network training. The performance was compared using various different descriptor sets and descriptor combinations based on the 120 standard Ghose-Crippen fragment descriptors, a wide range of 180 different properties and physicochemical descriptors from the Molecular Operating Environment (MOE) package, and 225 topological pharmacophore (CATS) descriptors. For the complete set of 525 descriptors cross-validated classificati...
531 citations
TL;DR: The role of number of images and significance of hyperparameters namely minibatch size, weight and bias learning rate in the classification accuracy and execution time have been analyzed.
334 citations
TL;DR: A Convolution Neural Network based approach is applied for the disease detection and classification of tomato and the experimental results shows the efficacy of the proposed model over pre-trained model i.e. VGG16, InceptionV3 and MobileNet.
195 citations
01 Aug 2018
TL;DR: This paper adopts a slight variation of the convolutional neural network model called LeNet to detect and identify diseases in tomato leaves and has achieved an average accuracy of 94–95 % indicating the feasibility of the neural network approach even under unfavourable conditions.
Abstract: The tomato crop is an important staple in the Indian market with high commercial value and is produced in large quantities. Diseases are detrimental to the plant's health which in turn affects its growth. To ensure minimal losses to the cultivated crop, it is crucial to supervise its growth. There are numerous types of tomato diseases that target the crop's leaf at an alarming rate. This paper adopts a slight variation of the convolutional neural network model called LeNet to detect and identify diseases in tomato leaves. The main aim of the proposed work is to find a solution to the problem of tomato leaf disease detection using the simplest approach while making use of minimal computing resources to achieve results comparable to state of the art techniques. Neural network models employ automatic feature extraction to aid in the classification of the input image into respective disease classes. This proposed system has achieved an average accuracy of 94–95 % indicating the feasibility of the neural network approach even under unfavourable conditions.
159 citations