检索结果-内蒙古大学图书馆

Automatic Lung Segmentation in Chest X-Ray images Using SAM With Prompts From YOLO

IEEE ACCESS 2024年 12卷 122805-122819页

作者： Khalili, Ebrahim Priego-Torres, Blanca Leon-Jimenez, Antonio Sanchez-Morillo, Daniel Univ Cadiz Dept Engn Automat Elect & Comp Architecture & Netw Puerto Real 11519 Spain Biomed Res & Innovat Inst Cadiz INiBICA Cadiz 11009 Spain Puerta del Mar Univ Hosp Pulmonol Dept Cadiz 11009 Spain

Despite the impressive performance of current deep learning models in the field of medical imaging, transferring the lung segmentation task in X-ray images to clinical practice is still a pending task. In this study, the performance of a fully automatic framework for lung field segmentation in chest X-ray images was evaluated. The framework is rooted in the combination of the Segment Anything Model (SAM) with prompt capabilities, and the You Only Look Once (YOLO) model to provide effective prompts. Transfer learning, loss functions, and several validation strategies were thoroughly assessed. This provided a complete benchmark that enabled future research studies to fairly compare new segmentation strategies. The results achieved demonstrated significant robustness and generalization capability against the variability in sensors, populations, disease manifestations, device processing, and imaging conditions. The proposed framework was computationally efficient, could address bias in training over multiple datasets, and had the potential to be applied across other domains and modalities.

关键词： Lung image segmentation Solid modeling Data models X-ray imaging YOLO Biomedical imaging deep learning Biomedical X-ray imaging image segmentation lung deep learning

来源：评论

学校读者我要写书评

暂无评论

TrioConvTomatoNet-BiLSTM: An Efficient Framework for the Classification of Tomato Leaf Diseases in real time Complex Background images

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2025年第1期18卷 1-28页

作者： Ledbin Vini, S. Rathika, P. PSN Coll Engn & Technol ECE Dept Tirunelveli 627152 India

Tomatoes are the most valuable vegetable worldwide that suffer from leaf diseases, which affect long-term tomato protection. So, to protect the tomato plants from the leaf diseases, it is essential to perform appropriate control measures through early and accurate categorization of leaf diseases. Recently, automated deep learning-based methods, including convolutional neural networks (CNNs), guaranteed accurate and timely classification of tomato leaf diseases. However, CNNs primarily capture local context features within a limited receptive field, making them effective for uniform background images. To handle complex background images, utilizing local and global context features is essential for accurate classification. To do so, it is essential to hybrid CNN architecture with other deep learning modules. This work suggests the TrioConvTomatoNet-BiLSTM framework, a hybridization of CNN architecture named TrioConvTomatoNet with a sequence module named bidirectional long short-term memory (BiLSTM). The proposed framework integrated both local and global context features for the precise classification of images with complex backgrounds. As a result, the proposed framework achieves remarkable accuracy of 99.65%, 98.83%, and 99.20% in classifying tomato leaf disease images with non-uniform, synthetic, and real-time complex backgrounds against the TrioConvTomatoNet and TrioConvTomatoNet-LSTM frameworks. Despite the fact that it requires a lesser number of training parameters and attained maximum accuracy over other existing hybrid approaches, expresses its superiority, robustness, and practical applicability. These features highlight the potential of the proposed framework in the emerging field of smart agriculture by enabling smartphone-based classification of tomato leaf diseases with real-life scenarios.

关键词： image processing Tomato leaf disease classification Smart agriculture deep learning Hybrid model

来源：评论

学校读者我要写书评

暂无评论

Object classification and visualization with edge artificial intelligence for a customized camera trap platform

引用

ECOLOGICAL INFORMATICS 2024年 79卷

作者： Nazir, Sajid Kaleem, Mohammad Glasgow Caledonian Univ Sch Comp Engn & Built Environm Glasgow City Scotland COMSATS Univ Dept Elect & Comp Engn Islamabad Pakistan Glasgow Caledonian Univ Cowcaddens Rd Glasgow G4 0BA Scotland

The camera traps have revolutionized the image and video capture in ecology and are often used to monitor and record animal presence. With miniaturization of low power electronic devices, better battery technologies, and software advancements, it has become possible to use the edge devices, such as Raspberry Pi as camera traps that can not only capture images and videos, but can also enable sophisticated image processing, and off-site communications. These developments can help to provide near real-time insights and reduce the manual processing of images. The on-board image classification and visualization is facilitated by the advancements in the deep Neural Networks (DNN), transfer learning approaches, and software libraries. This paper provides an investigation of image classification with transfer learning approaches using pretrained DNN models, and visualizations with Explainable Artificial Intelligence (XAI) techniques on Raspberry Pi Zero (RPi-Z) edge device. The MobileNetV2 model was used for image classification on the Florida-Part1 dataset obtaining the results for precision, recall, and F1-score as 0.95, 0.96, and 0.95 respectively. We also compared the model performance of MobileNetV2, EfficientNetV2B0, and MobileViT models for classification on the Extinction dataset with the best results for precision, recall, and F1-score as 0.97, 0.96, and 0.96 respectively, obtained with the EfficientNetV2B0 model. Two XAI techniques, Gradient-weighted-Class Activation Mapping (Grad-CAM) and Occlusion Sensitivity were used for visualization through heatmaps, to highlight the relative importance of the image areas contributing to the DNN model's prediction, that can also help to understand the model's performance and bias. The results provide practical use case scenarios for utilizing the transfer learning approaches, model optimization and deployment to edge devices, and model visualizations in ecological research.

关键词： Data science Computer vision deep learning Model generalization Fine tuning Explainable AI Hyperparameter tuning Vision transformers

来源：评论

学校读者我要写书评

暂无评论

A Novel image Classification Approach via MobileNet Model for Security Assessment of Power System

引用

ELECTRIC POWER COMPONENTS AND SYSTEMS 2024年

作者： Singh, Mahesh Pal Sinha, Nidul Natl Inst Technol Silchar Dept Elect Engn Silchar Assam India

The computational complexities of conventional techniques used for security assessment of power system are addressed by proposing a maiden deep learning-based technique capable of boosting security calculations, increasing decision-making efficiency, and reducing hazards for real time operation. This approach uses MobileNet Convolutional Neural Network (MCNN) to evaluate security with reduced model size and computational burden as compared to traditional CNN architectures by leveraging special type of convolution technique. MCNN's automatic feature extraction and strong generalization allow the operator to determine whether the current operating state of power system is secured or not. All of the system's critical operational scenarios are developed via load flow studies for generation of data while accounting for small signal stability with l-1 security and converted into RGB images of varied input dimensions for training and testing of the MCNN. Once trained, the MCNN is well-suited for real-time applications like assessing whether current state of the system is secured or not including unforeseen occurrences like topological changes in a computation-free manner. The comparative performance of the proposed method with customized CNN on three typical IEEE test system demonstrates its superior performance in terms of better accuracy and computational efficiency.

关键词： MobileNet security assessment image generation deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

FedDL: personalized federated deep learning for enhanced detection and classification of diabetic retinopathy

引用

PEERJ COMPUTER SCIENCE 2024年 10卷 e2508-e2508页

作者： Bhulakshmi, Dasari Rajput, Dharmendra Singh Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore Tamil Nadu India

Diabetic retinopathy (DR) is a condition that can lead to vision loss or blindness and is an unavoidable consequence of diabetes. Regular eye examinations are essential to maintaining a healthy retina and avoiding eye damage. In developing countries with a shortage of ophthalmologists, it is important to find an easier way to assess fundus photographs taken by different optometrists. Manual grading of DR is timeconsuming and prone to human error. It is also crucial to securely exchange patients' fundus image data with hospitals worldwide while maintaining confidentiality in real time. deep learning (DL) techniques can enhance the accuracy of diagnosing DR. Our primary goal is to develop a system that can monitor various medical facilities while ensuring privacy during the training of DL models. This is made possible through federated learning (FL), which allows for the sharing of parameters instead of actual data, employing a decentralized training approach. We are proposing federated deep learning (FedDL) in FL, a research paradigm that allows for collective training of DL models without exposing clinical information. In this study, we examined five important models within the FL framework, effectively distinguishing between DR stages with the following accuracy rates: 94.66%, 82.07%, 92.19%, 80.02%, and 91.81%. Our study involved five clients, each contributing unique fundus images sourced from publicly available databases, including the Indian Diabetic Retinopathy image Dataset (IDRiD). To ensure generalization, we used the Structured Analysis of the Retina (STARE) dataset to train the ResNet50 model in a decentralized learning environment in FL. The results indicate that implementing these algorithms in an FL environment significantly enhances privacy and performance compared to conventional centralized learning methods.

关键词： Diabetic retinopathy Fundus photographs deep learning Federated learning Federated average IDRiD STARE Convolutional neural networks Adaptive deep learning Federated deep learning

来源：评论

学校读者我要写书评

暂无评论

MASK-BASED INVISIBLE BACKDOOR ATTACKS ON OBJECT DETECTION 31

MASK-BASED INVISIBLE BACKDOOR ATTACKS ON OBJECT DETECTION

引用

2024 International Conference on image processing

作者： Shin, Jeongjin

ISBN: (纸本)9798350349405;9798350349399

deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks. These attacks prompt models to behave similarly to standard models without a trigger;however, they act maliciously upon detecting a predefined trigger. Despite extensive research on backdoor attacks in image classification, their application to object detection remains relatively underexplored. Given the widespread application of object detection in critical real-world scenarios, the sensitivity and potential impact of these vulnerabilities cannot be overstated. In this study, we propose an effective invisible backdoor attack on object detection utilizing a mask-based approach. Three distinct attack scenarios were explored for object detection: object disappearance, object misclassification, and object generation attack. Through extensive experiments, we comprehensively examined the effectiveness of these attacks and tested certain defense methods to determine effective countermeasures. Code is available at https://***/jeongjin0/invisible- backdoor-object-detection

关键词： Backdoor attack invisible attack object detection security in deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on deep learning-Based Data Fusion

引用

IEEE ACCESS 2024年 12卷 180093-180124页

作者： Hussain, Mazhar O'Nils, Mattias Lundgren, Jan Mousavirad, Seyed Jalaleddin Mid Sweden Univ STC Res Ctr S-85170 Sundsvall Sweden

The rapid progress in sensor technology and computational capabilities has significantly improved real-time data collection, enabling precise monitoring of various phenomena and industrial processes. However, the volume and complexity of heterogeneous data present substantial processing challenges. Traditional data-processing techniques, such as data aggregation, filtering, and statistical analysis, are increasingly supplemented by data fusion methods. These methods can be broadly categorised into traditional analytics-based approaches, like the Kalman Filter and Particle Filter, and learning-based approaches, utilising machine learning and deep learning techniques such as Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN). These techniques combine data from multiple sources to provide a comprehensive and accurate representation of information, which is critical in number of fields. Despite this, a comprehensive review of learning-based, particularly deep learning-based, data fusion strategies is lacking. This paper presents a thorough review of deep learning-based data fusion methodologies across various fields, examining their evolution over the past five years. It highlights applications in remote sensing, healthcare, industrial fault diagnosis, intelligent transportation, and other domains. The paper categories fusion strategies into early-level, intermediate-level, late-level, and hybrid fusion, emphasising their synergies, challenges, and suitability. It outlines significant advancements, the comparative advantages of deep learning-based methods over traditional approaches, and emerging trends and future directions. To ensure a comprehensive analysis, the review is structured using the ProKnow-C methodology, a rigorous selection process that focuses on relevant literature from recent years.

关键词： Data integration Reviews Portfolios Databases Remote sensing Market research Laser radar deep learning Systematics Support vector machines Data fusion deep learning early-level fusion intermediate-level feature fusion late level decision fusion hybrid fusion review

来源：评论

学校读者我要写书评

暂无评论

A Novel deep learning-Based Approach for Defect Detection of Synthetic Leather Using Gaussian Filtering

引用

IEEE ACCESS 2024年 12卷 196702-196714页

作者： Mai, Christopher Penava, Pascal Buettner, Ricardo Univ Fed Armed Forces Hamburg Helmut Schmidt Univ Chair Hybrid Intelligence D-22043 Hamburg Germany

Synthetic leather is a commonly used material, especially in the clothing industry. It is employed in the production of footwear, such as shoes and boots, as well as handbags and other accessories. Prior to exportation, the leather is subjected to a series of processing stages, which may result in the formation of surface defects. Quality assurance, which serves to identify defective leather in a timely manner, is still partially conducted by humans. This step is time-consuming and is associated with a higher error rate. To address these challenges, the deployment of image processing systems for the automated inspection of leather defects is becoming increasingly crucial. The objective of this study is to develop an effective deep learning model for the classification of defective synthetic leather, with the aim of implementing it in the quality control of synthetic leather production. To this end, a variety of architectural approaches are employed, including Xception, InceptionV3, ResNet50V2, VGG19, and VGG16. In addition to hyperparameter tuning, all architectures utilize transfer learning. Moreover, the impact of the Gaussian filter as a pre-processing step for images is examined. The results show that by using an innovative Gaussian filtering approach, an accuracy of 100% was achieved with the VGG16 model. Furthermore, the results show that the filtering approach has a positive influence on the accuracy of all other models. The high accuracies of the deep learning models show that the use of machine vision systems for the automatic inspection of defects in the synthetic leather industry is an effective economic step for companies, as it leads to cost and time savings in production due to the high classification performance. This study provides an overview of the results achieved and other key performance indicators for all the models used.

关键词： Production Transfer learning deep learning Defect detection Accuracy Inspection Information filters Supervised learning Gaussian filter synthetic leather defect detection transfer learning pre-trained architectures data augmentation hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Research on weld seam feature extraction and defect identification technology

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2024年

作者： Shang, Fei Cai, Dandan Sun, Bo Han, Yongquan Yang, Mingyuan Zhan, Chunying Inner Mongolia Univ Sci & Technol Sch Mech Engn Baotou Peoples R China Inner Mongolia Univ Sci & Technol Inner Mongolia Key Lab Intelligent Diag & Control Baotou Peoples R China Inner Mongolia Univ Sci & Technol Sch Mat & Met Baotou Peoples R China Inner Mongolia Inst Special Equipment Inspect & Re Baotou Branch Baotou Peoples R China Baotou North Sait Testing Technol Co Special Equipment Inspect & Testing Ctr Baotou Peoples R China

The quality of weld seams is a core factor affecting the performance of welded components, significantly impacting the safety and reliability of weldment structures. It holds considerable importance in quality control and cost management. Therefore, weld seam inspection is an indispensable part of industrial manufacturing and a key topic in non-destructive testing. This paper comprehensively summarises the main research results in weld seam feature extraction and defect identification based on systematic and detailed literature research. Firstly, the paper compares current mainstream non-destructive testing technologies, such as ultrasonic testing, radiographic testing, and infrared thermography, regarding detection principles, performance accuracy, and efficiency. It summarises their applicable scopes, as well as their advantages and disadvantages, and briefly introduces image processing-based methods for weld seam feature extraction. Secondly, a discussion and analysis of weld defect recognition are carried out, focusing on intelligent recognition methods based on deep learning, such as convolutional neural networks, generative adversarial networks, YOLO, etc. Finally, the outlook and future research trends are presented from various perspectives, such as real-time, adaptability, intelligence, etc. to provide a theoretical basis and technical support for welding quality control and structural safety assessment.

关键词： Weld seam inspection defect recognition non-destructive testing image processing feature extraction deep learning

来源：评论

学校读者我要写书评

暂无评论

WaveletFormerNet: A Transformer-based wavelet network for real-world non-homogeneous and dense fog removal

引用

image AND VISION COMPUTING 2024年 146卷

作者： Zhang, Shengli Tao, Zhiyong Lin, Sen Liaoning Tech Univ Sch Elect & Informat Engn Huludao Liaoning Peoples R China Shenyang Ligong Univ Sch Automat & Elect Engn Shenyang Liaoning Peoples R China

Although deep convolutional neural networks have achieved remarkable success in removing synthetic fog, it is essential to be able to process images taken in complex foggy conditions, such as dense or non-homogeneous fog, in the real world. However, the haze distribution in the real world is complex, and downsampling can lead to color distortion or loss of detail in the output results as the resolution of a feature map or image resolution decreases. Moreover, the over-stacking of convolutional blocks might increase the model complexity. In addition to the challenges of obtaining sufficient training data, overfitting can also arise in deep learning techniques for foggy image processing, which can limit the generalization abilities of the model, posing challenges for its practical applications in real-world scenarios. Considering these issues, this paper proposes a Transformer-based wavelet network (WaveletFormerNet) for real-world foggy image recovery. We embed the discrete wavelet transform into the Vision Transformer by proposing the WaveletFormer and IWaveletFormer blocks, aiming to alleviate texture detail loss and color distortion in the image due to downsampling. We introduce parallel convolution in the Transformer block, which allows for the capture of multi-frequency information in a lightweight mechanism. Such a structure reduces computational expenses and improves the effectiveness of the network. Additionally, we have implemented a feature aggregation module (FAM) to maintain image resolution and enhance the feature extraction capacity of our model, further contributing to its impressive performance in real-world foggy image recovery tasks. Through extensive experiments on real-world fog datasets, we have demonstrated that our WaveletFormerNet achieves superior performance compared to state-of-the-art methods, as shown through quantitative and qualitative evaluations of minor model complexity. Additionally, our satisfactory results on real-world dust remov

关键词： image dehazing Convolution neural network Wavelet transform Swin transformer Fog removal

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：