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

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

PurposeSemantic segmentation is a fundamental part of the surgical application of deep learning. Traditionally, segmentation in vision tasks has been performed using convolutional neural networks (CNNs), but the transformer architecture has recently been introduced and widely investigated. We aimed to investigate the performance of deep learning models in segmentation in robot-assisted radical prostatectomy (RARP) and identify which of the architectures is superior for segmentation in robotic surgery.Materials and MethodsIntraoperative images during RARP were obtained. The dataset was randomly split into training and validation data. Segmentation of the surgical instruments, bladder, prostate, vas and seminal vesicle was performed using three CNN models (DeepLabv3, MANet, and U-Net++) and three transformers (SegFormer, BEiT, and DPT), and their performances were analyzed.ResultsThe overall segmentation performance during RARP varied across different model architectures. For the CNN models, DeepLabV3 achieved a mean Dice score of 0.938, MANet scored 0.944, and U-Net++ reached 0.930. For the transformer architectures, SegFormer attained a mean Dice score of 0.919, BEiT scored 0.916, and DPT achieved 0.940. The performance of CNN models was superior to that of transformer models in segmenting the prostate, vas, and seminal vesicle.ConclusionsDeep learning models provided accurate segmentation of the surgical instruments and anatomical structures observed during RARP. Both CNN and transformer models showed reliable predictions in the segmentation task; however, CNN models may be more suitable than transformer models for organ segmentation and may be more applicable in unusual cases. Further research with large datasets is needed.

We propose a practical Convolution Neural Network (CNN) model termed the CNN for Semantic Segmentation for driver Assistance system (CSSA). It is a novel semantic segmentation model for probabilistic pixel-wise segmentation, which is able to predict pixel-wise class labels of a given input image. Recently, scene understanding has turned out to be one of the emerging areas of research, and pixel-wise semantic segmentation is a key tool for visual scene understanding. Among future intelligent systems, the Advanced Driver Assistance System (ADAS) is one of the most favorite research topic. The CSSA is a road scene understanding CNN that could be a useful constituent of the ADAS toolkit. The proposed CNN network is an encoder-decoder model, which is built on convolutional encoder layers adopted from the Visual Geometry Group’s VGG-16 net, whereas the decoder is inspired by segmentation network (SegNet). The proposed architecture mitigates the limitations of the existing methods based on state-of-the-art encoder-decoder design. The encoder performs convolution, while the decoder is responsible for deconvolution and un-pooling/up-sampling to predict pixel-wise class labels. The key idea is to apply the up-sampling decoder network, which maps the low-resolution encoder feature maps. This architecture substantially reduces the number of trainable parameters and reuses the encoder’s pooling indices to up-sample to map pixel-wise classification and segmentation. We have experimented with different activation functions, pooling methods, dropout units and architectures to design an efficient CNN architecture. The proposed network offers a significant improvement in performance in segmentation results while reducing the number of trainable parameters. Moreover, there is a considerable improvement in performance in comparison to the benchmark results over PASCAL VOC-12 and the CamVid.

It is crucial that the situation of railway scene needs to be periodically monitored to ensure railway safety. Usually, the camera is placed in the driver's cab on a moving vehicle to generate a large number of high-resolution images of railway scene. The traditional image processing inspection methods can only inspect railway scene of the local and simple background. They are feasible sometimes, but not universal and efficient. In this paper, a novel and practical approach is proposed to visual railway scene detection with Deep Semantic Segmentation Convolutional Neural Networks(DSSCNN). It is helpful for precisely locating and detailedly describe important parts of the railway scene in the entire image instead of separately detecting like traditional methods. In addition, three particular blocks named Conv Block, Dilated Conv Block, and Sum Block in DSSCNN are designed to extract more context information from railway images and enhance the segmentation performance. It shows that DSSCNN trained end-to-end and encoder-decoder network structure for semantic segmentation of railway scene are more superior than UNet and Fully Convolutional Networks(FCN) on the same datasets. At the same time, it is also verified that it is feasible and efficient to describe, visual and locate the key parts of the railway scene by DSSCNN.

Semantic segmentation is a fundamental task in remote sensing image understanding. Recently, Deep Convolutional Neural Networks (DCNNs) have considerably improved the performance of the semantic segmentation of natural scenes. However, it is still challenging for very high-resolution remote sensing images. Due to the large and complex scenes as well as the influence of illumination and imaging angle, it is particularly difficult for the existing methods to accurately obtain the category of pixels at object boundaries—the so-called boundary blur. We propose a framework called Boundary-Aware Semi-Supervised Semantic Segmentation Network (BAS <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> Net), which obtains more accurate segmentation results without additional annotation workload, especially at the object boundaries. The Channel-weighted Multi-scale Feature (CMF) module balances semantic and spatial information, and the Boundary Attention Module (BAM) weights the features with rich semantic boundary information to alleviate the boundary blur. Additionally, to decrease the amount of difficult and tedious manual labeling of remote sensing images, a discriminator network infers pseudolabels from unlabeled images to assist semisupervised learning, and further improves the performance of the segmentation network. To validate the effectiveness of the proposed framework, extensive experiments have been performed on both the ISPRS Vaihingen dataset, and the novel remote sensing dataset AIR-SEG with more categories, and complex boundaries. The results demonstrate a significant improvement of accuracy especially on boundaries and for small objects.

Rice is the staple food in Bangladesh. Every year many crops are lost because of the disease of the rice plant. Our farmers are facing a great loss every year as well as rice productivity is declining. Some diseased and healthy leaf images of rice plants have been collected. The images have been classified into four classes. The classes are Brown Spot, Hispa, Leaf Blast diseased leaves, and Healthy leaves, usually known as Oryza Saiva diseases of rice. Deep learning is very common and popular to analyze and make predictions from these kind of image data. In this research, the CNN (Convolutional Neural Network) models have been used to predict the classes. Among various CNN models, VGG16, MobileNet, ResNet50, and DenseNet121 pre-trained models have been applied. Among those pre-trained models, the highest accuracy 95.3% has been found from the VGG16 model. In addition, an Android mobile app has been developed using the highest performant VGG16 trained model. Using this mobile app, farmers will be able to upload a photo and predict the disease of that rice plant or not in a convenient way.

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.

Nowadays, Intelligent Transportation System (ITS) has become one of the most popular subjects of scientific research. ITS provides innovative services to transport and traffic monitoring like vehicle segmentation and classification. Image understanding and object semantic segmentation in traffic scenes is a very important topic in the trend of autonomous driving issues, like autonomous vehicles and robotics. Actually, Deep Convolution Neural Network (CNN) architectures have given very good results and good performance in computer vision tasks such as classification, object detection, and segmentation. In this scope, we can distinguish two modes of CNN training, the pre-trained model and the training from scratch. In fact, deep neural network training without pre-trained weights and little data requires more training iterations. Besides, deeper models are more efficient than their shallow counterparts for the task of semantic segmentation. In this paper, we will make a comparative study between many deep CNNs models that can train the CNN model from scratch on small datasets, in addition, we will use data augmentation techniques. Extensive experiments were performed on the MiniCity urban scene dataset to prove the effectiveness of the used neural networks while obtaining promising results.

A case study on computer-aided diagnosis of nonerosive reflux disease using deep learning techniques

Three-channel convolutional neural networks for vegetable leaf disease recognition

Effective disease control in crops is essential for ensuring food security, as numerous diseases can significantly reduce agricultural productivity. Leaf disease is a crucial determinant of crop yield and quality. Potatoes are widely regarded as a vital staple in diets around the world. Potato blight, often known as late blight, is a severe disease impacting Solanaceae plants, particularly the potato. The oomycete Phytophthora infestans serves as the causal agent, posing a significant threat to potato crops by reducing yields and leading to financial losses. Identifying potato diseases is essential for ensuring food security and minimizing economic losses in agriculture. Numerous studies have explored the applications of machine learning and deep learning technologies for detecting blight diseases in affected crops. The proposed methodology outlined in our study offers a promising and effective means to enhance the accuracy of potato late blight classification. Advancements in technology can significantly improve the identification and treatment of diseases. Deep learning algorithms have been effectively employed in a range of practical applications. In our investigation, convolutional neural network models are used to analyze images of leaves. The primary aim of this initiative is to gain insights into and enhance the capacity to recognize diseases in their early phases. After the input images undergo preprocessing, the target region is distinctly isolated. CNN examines images to identify unique features, including edges, colours, and textures. This study evaluates the effectiveness of the proposed model through a diverse dataset of potato leaf images, making essential contributions to the domain of automated disease detection systems. The results of this study could enhance techniques for agricultural management and strengthen the sustainability of agriculture. This study introduces an improved CNN model designed to identify the blight disease state in potato leaf images, providing a valuable tool for farmers. The findings may aid in the evaluation and implementation of Convolutional Neural Network (CNN) models for classifying proximal sensing images of potato plant leaves. Additional investigations could leverage this modelling framework and have the opportunity to examine various other factors to identify leaf infections at an earlier stage for crop protection.

Background: Plant diseases affect agricultural output, quality and profitability, making them serious obstacles for agriculture. It is essential to detect diseases early in order to reduce losses while retaining sustainable practices. Plant disease detection has benefited greatly from the use of computer vision and deep learning in recent years because of their outstanding precision and computing capability. Objective: In this paper, we intend to investigate the role of deep learning in computer vision for plant disease detection while looking into how these techniques address complex disease identification problems. A variety of deep learning architectures were reviewed, and the contribution of frameworks such as Tensorflow, Keras, Caffe and PyTorch to the researchers' model construction was studied as well. Additionally, the usage of open repositories such as PlantVillage and Kaggle along with the customized datasets were discussed. Methods: We gathered the most recent developments in deep learning techniques for leaf disease detection through a systematic literature review of research papers published over the past decade, using reputable academic databases like Scopus and Web of Science, following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) method for guidance. Results: This study finds that researchers consistently enhance existing deep learning architectures to improve prediction accuracy in plant disease detection, often by introducing novel architectures and employing transfer learning methods. Frameworks like TensorFlow, Keras, Caffe, and PyTorch are widely favored for their efficiency in development. Additionally, most studies opt for public datasets such as PlantVillage, Kaggle, and ImageNet, which offer an abundance of labelled data for training and testing deep learning models. Conclusion: While no singular ‘best' model emerges, the adaptability of deep learning and computer vision demonstrates the dynamic nature of plant disease recognition area, and this paper provides a comprehensive overview of deep learning's transformative impact on plant disease recognition by bringing together information from different studies. Keywords: Deep learning, Computer vision, Plant disease, Systematic literature review

Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very costly and time-consuming to collect. In this paper, we propose a method for learning CNNbased semantic segmentation models from images with several types of annotations that are available for various computer vision tasks, including image-level labels for classification, box-level labels for object detection and pixel-level labels for semantic segmentation. The proposed method is flexible and can be used together with any existing CNNbased semantic segmentation networks. Experimental evaluation on the challenging PASCAL VOC 2012 and SIFTflow benchmarks demonstrate that the proposed method can effectively make use of diverse training data to improve the performance of the learned models.

The care and health of agricultural plants, which are the primary source for people to eat healthily, are essential. Disease detection in plants is one of the critical elements of smart agriculture. In parallel with the development of artificial intelligence, advancements in smart agriculture are also progressing. The development of deep learning techniques positively affects smart farming practices. Today, using deep learning and computer vision techniques, various plant diseases can be detected from images such as photographs. In this research, deep learning techniques were used to detect and diagnose bean leaf diseases. Healthy and diseased bean leaf images were used to train the convolutional neural network (CNN) model, which is one of the deep learning techniques. Transfer learning was applied to CNN models to detect plant diseases with the difference of related works. A transfer learning-based strategy to identify various diseases in plant varieties is demonstrated using leaf images of healthy and diseased plants from the Bean dataset. With the proposed method, 1295 images were studied. The results show that our technique successfully identified disease status in bean leaf images, achieving an accuracy of 98.33% with the ResNet50 model.

Rice disease prediction plays important task for automated rice disease recognition systems. Feature extraction and classification based on deep learning play important tasks in vision-based diseases recognition. The advancement of deep convolutional neural network using mage data illustrates the approach for identification of rice diseases using deep features with the expectation of high returns. Instead of fine-tuning task which concerns estimation of internal parameters of a model to adjust precisely with certain observations. This paper focuses on extrinsic parameters for model training, which utilities for improving precise of recognition system. Some pretrain models AlexNet, ResNet101 were implemented as mainstream of the convolutional neural network (CNN) architecture. Our approach directly estimates locations of features based on deep learning classification for of rice leaf diseases recognition. There are four kinds of the rice diseases investigated, such as rice blast, bacterial leaf blight, alum poisoning, and leaf folder. A large dataset resolution images from real scenes in the farm were collected for training and evaluation. In this study, the augmentation of image also applied for evaluation input images. The output prediction results of set samples are used for voting final decision. The experimental results show that the proposed approach with hyperparameters customization and data augmentation outperforms.KeywordsDeep learningSmart agriculturalRice leaf diseases