Tomato leaf disease recognition based on improved convolutional neural network with attention mechanism

The identification of plant leaf diseases is crucial in precision agriculture, playing a pivotal role in advancing the modernization of agriculture. Timely detection and diagnosis of leaf diseases for preventive measures significantly contribute to enhancing both the quantity and quality of agricultural products, thereby fostering the in-depth development of precision agriculture. However, despite the rapid development of research on plant leaf disease identification, it still faces challenges such as insufficient agricultural datasets and the problem of deep learning-based disease identification models having numerous training parameters and insufficient accuracy. This paper proposes a plant leaf disease identification method based on improved SinGAN and improved ResNet34 to address the aforementioned issues. Firstly, an improved SinGAN called Reconstruction-Based Single Image Generation Network (ReSinGN) is proposed for image enhancement. This network accelerates model training speed by using an autoencoder to replace the GAN in the SinGAN and incorporates a Convolutional Block Attention Module (CBAM) into the autoencoder to more accurately capture important features and structural information in the images. Random pixel Shuffling are introduced in ReSinGN to enable the model to learn richer data representations, further enhancing the quality of generated images. Secondly, an improved ResNet34 is proposed for plant leaf disease identification. This involves adding CBAM modules to the ResNet34 to alleviate the limitations of parameter sharing, replacing the ReLU activation function with LeakyReLU activation function to address the problem of neuron death, and utilizing transfer learning-based training methods to accelerate network training speed. This paper takes tomato leaf diseases as the experimental subject, and the experimental results demonstrate that: (1) ReSinGN generates high-quality images at least 44.6 times faster in training speed compared to SinGAN. (2) The Tenengrad score of images generated by the ReSinGN model is 67.3, which is improved by 30.2 compared to the SinGAN, resulting in clearer images. (3) ReSinGN model with random pixel Shuffling outperforms SinGAN in both image clarity and distortion, achieving the optimal balance between image clarity and distortion. (4) The improved ResNet34 achieved an average recognition accuracy, recognition precision, recognition accuracy (redundant as it's similar to precision), recall, and F1 score of 98.57, 96.57, 98.68, 97.7, and 98.17%, respectively, for tomato leaf disease identification. Compared to the original ResNet34, this represents enhancements of 3.65, 4.66, 0.88, 4.1, and 2.47%, respectively.

This composition bargains with the Tomato leaf infection discovery and classification utilizing different strategies like Convolutional Neural Network (CNN), Regions with CNN (R-CNN), Fast R-CNN and Faster R-CNN. The main issue in the agricultural sector is leaf diseases, which have an impact on crop yield and financial gain. Early detection of leaf diseases in plants is essential to prevent losses to the agricultural sector. There are several tomato leaf diseases that affect the crop's leaves, including the Mosaic virus, Early Blight, Healthy, Septoria leaf, and Bacterial spot. Using deep learning algorithms and image processing methods, we can identify the diseases in tomato leaves using developing deep learning approaches. The implementation procedures in our proposed work involves data collection, pre-processing, training, feature extraction, testing, and classification utilising the Visual Geometry Group (VGG 16) to identify damaged or healthy leaves. VGG 16 is incorporated to categorise the leaves as healthy or diseased based on the data and Regression's boundary box method is adopted. Therefore, using Faster RCNN, a model is created to identify and categorise diseases from every image of a tomato leaf that is used as an input, providing a forecast with a considerably greater degree of accuracy. We obtain an accuracy of approximately 98% after fitting the collected features into the neural network over 20 iterations.

A new approach to learning and recognizing leaf diseases from individual lesions using convolutional neural networks

In recent years, plant leaf diseases has become a widespread problem for which an accurate research and rapid application of deep learning in plant disease classification is required, tomato is also one of the most important plants and seeds which are used worldwide for cooking in either dried or fresh form, tomato are a great source of protein that offer many health benefits, but there are a lot of diseases associated with tomato leaf which hinder its production. Thus, an accurate classification of tomato leaf diseases is needed to solve the problem in the early stage. A deep learning approach is proposed to identify and classify leaf disease by using public dataset of leaf image and CNN model with the open source library TensorFlow. In this project, we proposed a method to classify tomato leaf disease and to find and describe the efficient network architecture (hyper parameters and optimization methods). Moreover, after applying each architecture separately, we compared their obtained results to find out the best architecture configuration for classifying tomato leaf diseases and their results. Furthermore, to satisfy the classification requirements, the model was trained using CNN architecture check if we could get faster training times, higher accuracy and easier retraining. Deep learning is a branch of artificial intelligence. In recent years, with the advantages of automatic learning and feature extraction, it has been widely concerned by academic and industrial circles. It has been widely used in image and video processing, voice processing, and natural language processing. At the same time, it has also become a research hotspot in the field of agricultural plant protection, such as plant disease recognition. The application of deep learning in plant disease recognition can avoid the disadvantages caused by artificial selection of disease spot features, make plant disease feature extraction more objective, and improve the research efficiency and technology transformation speed. This review provides the research progress of deep learning technology in the field of crop leaf disease identification in recent years. In this project, we present the current trends and challenges for the detection of plant leaf disease using deep learning and advanced imaging techniques. We hope that this project will be a valuable resource for researchers who study the detection of plant diseases. At the same time, we also discussed some of the current challenges and problems that need to be resolved.

Tomato plants are particularly vulnerable to leaf diseases, which can take a serious toll on crop yield and quality if not caught early. Traditionally, farmers and agricultural experts rely on manual inspection to spot these diseases a method that can be both slow and prone to mistakes. To streamline this process, our project introduces an automated system that uses machine learning and image processing to detect tomato leaf diseases more accurately and efficiently. We worked with a dataset of tomato leaf images that includes both healthy leaves and those affected by diseases like Early Blight, Late Blight, Leaf Mold, and Target Spot. Using this data, we trained a Convolutional Neural Network (CNN) to classify the images with high accuracy. To improve the model’s learning, we applied standard preprocessing steps such as image augmentation, resizing, and normalization. Our experiments show that the system performs well, offering reliable early detection of various tomato leaf diseases. By providing timely insights, this tool can help farmers take preventive action sooner, potentially reducing crop loss and improving productivity. In the future, we hope to expand this work into mobile platforms to make real- time disease detection more accessible in the field. Key Words: Tomato leaf diseases, disease detection, deep learning, CNN, image processing, Late blight, Leaf mold.

This study aims to detect leaf diseases in tomato plants by applying the Xception model in the Convolutional Neural Network (CNN) method. The study categorizes tomato conditions into three main categories: Early Blight, Late Blight, and Healthy. Early Blight is generally infected by specific pathogens that cause spots and damage in the early stages of plant growth, while Late Blight is infected by pathogens in the later stages of the growing season. Meanwhile, the healthy category indicates normal conditions without disease symptoms. The dataset used consists of 300 tomato images, with each category having 100 images. In the model training phase using the fit method in TensorFlow, 17 epochs were performed to teach the model to recognize patterns in tomato leaf disease images in the training dataset. The model testing results on 30 tomato leaf images showed an accuracy rate of 85.84%. This result indicates a positive indication that the developed CNN model performs well in detecting and classifying tomato leaf conditions. Thus, this research can contribute to improving the understanding and management of leaf diseases in tomato plants to support more productive and sustainable agriculture.

Plant diseases that can destructively harm the agriculture are usually spotted with bare eyes, and this may consume a longer time leaving a chance of incorrect detection. Early detection can solve this problem and reduces the risk of decreasing plant production. The central focus of this study is to automatically detect tomato plant leaf diseases in a faster way by implementing Deep Learning (DL), which can be effectively applied for image classification using different convolutional neural network (CNN) architectures. This paper offers to classify images via transfer learning architectures including VGG-16, VGG-19, and Inception-V3 models with CNN to identify diseases. Applying these models on a dataset containing 11000 images of tomato leaves including signs of 9 different diseases and healthy leaf, high accuracy is gained. Finally, the comparative analysis done on the three pre-trained models within this paper summarizes that the best-suited model for detecting tomato leaf diseases with the best accuracy is Inception-V3. In order to support the claim, necessary results and data are also included in this paper.

Tomato leaf pests and diseases pose a significant threat to the yield and quality of Q6 tomatoes, highlighting the necessity for comprehensive studies on effective control methods. Current control measures predominantly rely on experience and manual observation, hindering the integration of multi-source data. To address this, we integrated information resources related to tomato leaf pests and diseases from agricultural standards documents, knowledge websites, and relevant literature. Guided by domain experts, we preprocessed this data to construct a sample set. We utilized the Named Entity Recognition (NER) model ALBERT-BiLSTM-CRF to conduct end-to-end knowledge extraction experiments, which outperformed traditional models such as 1DCNN-CRF and BiLSTM-CRF, achieving a recall rate of 95.03%. The extracted knowledge was then stored in the Neo4j graph database, effectively visualizing the internal structure of the knowledge graph. We developed a digital diagnostic system for tomato leaf pests and diseases based on the knowledge graph, enabling graphical management and visualization of pest and disease knowledge. The constructed knowledge graph offers insights for controlling tomato leaf pests and diseases and provides new research directions for pest control in other crops.

Agriculture is the backbone of India and more than 50% of the population is dependent on it. With the increasing demand for food with the increase in population, it is the need of time that crops should be prevented against diseases. More than 1K acres of land with tomato diseases got affected in Pune only during this pandemic (2021). It could have been prevented by correct identification of the disease and then by corrective measures. This paper presents the experimental and comparative study of tomato leaf disease classification using various traditional machine learning algorithms like random forest (RF), support vector machines (SVM), naïve bayes (NB), and deep learning convolutional neural network (CNN) algorithm. In this study, it is perceived that CNN with a pre-trained Inception v3 model was able to detect and classify better than traditional methods with more than 95% accuracy.

The problems of plant leaf disease are rather serious in the world agricultural industry, leading to a significant decrease in crop quantity and quality, consequently, resulting in a huge loss in the economy and food insecurity. Detection and successful classification of plant diseases at the initial stage is essential to further agricultural output and the quality production of food. The recent improvements in the field of artificial intelligence (AI), specifically, machine learning (ML) and deep learning (DL), have shown significant prospects in automating and enhancing methods of diagnosing plant leaf diseases by using a wide variety of ML and DL algorithms. This review article presents an in-depth analysis of thirty novel methods created by researchers to diagnose and classify plant leaf diseases. They are such conventional classifiers as Support Vector Machines (SVM), Random Forests (RF), and K-Nearest Neighbors (KNN), along with some advanced DL architectures, such as Convolutional Neural Networks (CNN), VGG16, ResNet50, InceptionResNetV2, EfficientNet, and various hybrids. The review analysis takes into consideration the methodologies applied, performance metrics, and insights in practice, as well as the strengths and weaknesses of both. The most crucial findings of the review show that deep learning models, and CNNs in particular, tend to be more accurate, robust, and feature extractors than traditional models of MLs. The performance of classification is also enhanced by numerous hybrid models that will use ML together with DL, and transfer learning has been an effective method to enhance the generalization using small datasets. Nevertheless, with all this progress, the issues of diversity of datasets, computational resource requirements and model interpretability are still to be explored in the future.

Background: Plant diseases and pests were natural disasters that seriously threaten agricultural production. Leaf diseases posed a significant threat to the overall productivity and quality of apple orchards. Currently, the diagnosis of plant diseases in apple orchards mainly relied on manual labor, which was both time-consuming and costly. It took a considerable amount of time to train an expert capable of accurately identifying apple diseases and pests, and different crop diseases vary. However, with the use of AI technology, training could be completed in just a few hours to a day, transforming computers into experts in disease and pest identification. Although China became a major apple cultivation nation, the development data from 2021 revealed that traditional advantageous production areas were undergoing dynamic adjustments due to optimization of industrial structure, leading to a decrease in cultivated land. Conversely, the demand for apples in the Chinese market continued to rise, even as the country's population structure gradually trended towards an aging population. This situation underscored the urgent need to replace the laborious and high-cost task of identifying apple foliar diseases in the cultivation process with intelligent agricultural technological solutions. Taking into account the aforementioned factors of the natural environment and socio-cultural considerations and addressing the issue of reduced apple yields due to the high impact of foliar diseases, we initiated study on disease prevention and control during the cultivation process. Methods: To overcome the objective impact of environmental factors, the system extracted images and performed operations such as enhancement and segmentation. Subsequently, a convolutional neural network was employed to process the enhanced images, extracting features such as color, shape, and texture of apple foliar lesions, which were then summarized into histograms using mathematical methods. These histograms served as the primary reference for distinguishing various diseases. Python was chosen as the programming language for the system, and the recognition system was operated by integrating frontend technologies, backend database design, and other relevant techniques. Results: Based on a substantial number of experimental results, the apple leaf disease and nutrient deficiency recognition system could accurately and with extremely high precision identifying major diseases commonly occurring in apple plants, including apple scab, leaf spot disease, rust disease, gray mold disease, and brown spot disease. Moreover, the system was capable of proposing remedies tailored to the specific pain points of each disease. It not only detected apple leaf diseases but also performs nutrient deficiency detection. This holds significant importance in enhancing both the yield and quality of apples. Conclusion: For the commonly occurring foliar diseases in cultivation, the system exhibited the capability to autonomously recognize and provide decision feedback. In contrast to the less efficient and more costly traditional approach of consulting experts, the more accessible apple foliar disease recognition system was poised to replace it as a primary tool for prevention and control assistance. This system will serve as a guiding companion, safeguarding the robust growth of apple plants.

Smart Farming with the transformative potential of Artificial Intelligence has emerged as a promising breakthrough in enhancing the agricultural productivity. The rapid in supercomputing facilities has redefined Deep Learning and its applications are seemingly limitless. It involves the use of deeper neural networks for greater learning capabilities eventually resulting in higher performance and precision. Its ability to discern patterns at higher calibre made it penetrate into almost all applications of computer vision including the field of Agriculture for Plant leaf disease detection, fruit counting, water management, weed and pest control. This research work deals with the prediction of Tomato leaf diseases based on image classification, using pre-trained deep convolutional networks. The accuracy of the model is evaluated using standard classification metrics namely Accuracy, Precision, Recall and F1-score. Furthermore, this paper makes a recommendation on the best optimizing function among three standard optimizers for classification of tomato leaf diseases based on performance metrics.KeywordsDeep learningConvolutional Neural NetworkOptimizer functionTomatoPlant leaf diseases

Maize leaf disease recognition based on improved MSRCR and OSCRNet

Identifying and detecting a plant disease is a primary challenge in the farming segment. Specifically, for tomato farming: Early Blight, Late Blight, Mosaic Virus, Target Spot, Yellow Leaf Curl Virus (YLCV), Bacterial Spot, Leaf mold, Septoria leaf spot and two-spotted spider mite are nine general diseases that severely affect the yield. In this work, we propose convolutional neural networks (CNNs) based deep learning (DL) model for the identification of tomato leaf diseases. In our study, we take the Tomato Leaf Disease Dataset (TLDD) consisting of 18,160 images of the infected and the healthy tomato leaves from PlantVillage. We first select the most suitable and accurate deep learning models for disease identification experiments. Four popular models viz. SqueezeNet, ResNet50, InceptionV3 and DenseNet are chosen for the analysis. Lastly, using ImageAI library on Google Colaboratory (Colab), we train all the four models on the collected tomato-leaf-image dataset to identify the presence of above mentioned nine common tomato leaf diseases. Results from our experiments on the comparative study of the selected deep learning models identify nine different tomato leaf diseases. We infer that the InceptionV3 model provides the highest accuracy of 99.64%. Our chosen model provides faster detection with higher accuracy as compared to the other models. In future work, we intend to modify the algorithm to develop our own model for disease identification for other crops as well.KeywordsDeep learningConvolutional neural networkTomato leaf diseaseImageAI

<bold>Objective</bold> A multi-scale <italic>Camellia oleifera</italic> Leaf Disease Recognition Net（COLDR-Net）based on improved lightweight convolutional neural network ShuffleNet V2 was proposed to address the issue of low accuracy in image recognition of <italic>Camellia oleifera</italic> leaf diseases in natural environments. <bold>Method</bold> The model enhanced the disease spot feature information in the image with the embedded Efficient Channel Attention（ECA）.Additionally，a Multi-scale Feature Extraction（MEF）unit was designed to enhance the recognition ability of fine spots.Focal Loss was used to replace the Cross-Entropy Loss function，which alleviated the unbalanced distribution of sample categories leading to large differences in the effectiveness of the model for different categories of disease identification.The Mish activation function was used to avoid the problem of gradient disappearance when the input was negative and to improve the expression ability of the model.The network structure was optimized by trimming the number of network layers and optimizing the number of output channels to reduce the number of computations and model parameters to achieve the lightweight of the model. <bold>Result</bold> The results showed that the accuracy and F1-score of COLDR-Net on the disease dataset of <italic>Camellia oleifera</italic> leaf were 97.19% and 97.08%，respectively.Its accuracy was higher when compared with that of AlexNet（93.04%），VGG16（94.18%），ResNet18（94.5%），ResNet50（95.45%）and MobileNetV3-Large（93.41%）.The accuracy was 4.07% better than the model before improvement.The number of model parameters were 2.61M，the FLOPs were 0.24G，and the average inference time for a single image on the mobile devices were 67ms.The model was deployed on the mobile Android platform to develop a leaf disease identification system for <italic>Camellia oleifera</italic>. <bold>Conclusion</bold> The proposed COLDR-Net model effectively meets the demand for real-time identification of <italic>Camellia oleifera</italic> leaf diseases，which can provide valuable reference for disease control，diagnosis，and resource-constrained mobile terminals.