检索结果-内蒙古大学图书馆

An end-to-end deep learning approach for real-time single image dehazing

JOURNAL OF real-time image processing 2023年第1期20卷 12页

作者： Jeong, Chi Yoon Moon, KyeongDeok Kim, Mooseop Elect & Telecommun Res Inst Artificial Intelligence Res Lab 218 Gajeong Ro Daejeon 34129 South Korea Univ Sci & Technol Artificial Intelligence 217 Gajeong Ro Daejeon 34113 South Korea

image dehazing methods can restore clean images from hazy images and are popularly used as a preprocessing step to improve performance in various image analysis tasks. In recent times, deep learning-based methods have been used to sharply increase the visual quality of restored images, but they require a long computation time. The processing time of image-dehazing methods is one of the important factors to be considered in order not to affect the latency of the main image analysis tasks such as detection and segmentation. We propose an end-to-end network model for real-time image dehazing. We devised a zoomed convolution group that processes computation-intensive operations with low resolution to decrease the processing time of the network model without performance degradation. Additionally, the zoomed convolution group adopts an efficient channel attention module to improve the performance of the network model. Thus, we designed a network model using a zoomed convolution group to progressively recover haze-free images using a coarse-to-fine strategy. By adjusting the sampling ratio and the number of convolution blocks that make up the convolution group, we distributed small and large computational complexities respectively in the early and later operational stages. The experimental results with the proposed method on a public dataset showed a real-time performance comparable to that of another state-of-the-art (SOTA) method. The proposed network's peak-signal-to-noise ratio was 0.8 dB lower than that of the SOTA method, but the processing speed was 10.4 times faster.

关键词： Single-image dehazing Lightweight dehazing networks image restoration End-to-end learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The use of intelligent real-time image acquisition system using data mining technology in news acquisition and editing practice

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2024年第2期24卷 639-656页

作者： Ma, Xiaowen Shandong Univ Arts Lib Jinan Shandong Peoples R China

Aiming to address the timely dissemination of news information, this work explores the clever utilization of data mining (DM) technology and deep learning (DL) algorithms to construct an intelligent real-time news image acquisition system to meet the urgency of news dissemination needs. First, this work introduces an intelligent real-time news image acquisition system and provides a detailed analysis of its principles and advantages. Throughout this process, the crucial role of DM technology in news image classification and automation is emphasized, especially in dealing with rapidly evolving news events. Next, the work establishes an intelligent real-time news image acquisition model based on DL algorithms, which integrates the essence of DM technology. Through this fusion, the research objective is to enhance the performance of the news image acquisition system to achieve higher real-time and accuracy, which is vital for the swift delivery of news information. Finally, this work investigates the application of the intelligent news image acquisition system in network communication to ensure its adaptability to various network communication scenarios while maintaining accuracy and real-time capabilities. The research results demonstrate that the application of DM technology in combination with DL algorithms can effectively meet the practical needs of the news industry, enhancing the automation of news image processing and enabling faster information delivery to the audience. Notably, the AlexNet model employed performs exceptionally well, achieving recognition rates of up to 99.6% after data augmentation or equalization processing, with an accuracy of 90.9% and a high specificity of 93.38%. This indicates outstanding overall classification accuracy and negative class accuracy, even when distinguishing between news and non-news scenarios. These results clearly underscore the connection between DM technology and news acquisition and editing practices, and emphasize it

关键词： deep learning data mining real-time image acquisition network security AlexNet model

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning and Fuzzy Matching for real-time Bidirectional Arabic Sign Language Translation: Toward Inclusive Communication Technologies

引用

IEEE ACCESS 2025年 13卷 94118-94136页

作者： Mosleh, Mogeeb A. A. Mohammed, Ahmed A. A. Esmail, Ezzaldeen E. A. Mohammed, Rehab A. A. Almuhaya, Basheer Univ Sci & Technol Fac Engn & Comp Dept Informat Technol Aden Yemen Taiz Univ Dept Software Engn Taizi Yemen

Technological advances and AI tools can help address the challenges faced by individuals who are deaf or nonverbal in different areas of social interaction. Existing tools mainly focus on one-way translation and are limited by small vocabulary datasets, require significant computational power, and often lack a real-time implementation. Therefore, a bidirectional real-time translation application for Arabic Sign Language and written Arabic text was developed in this research to improve communication and learning experiences for individuals who are deaf. The proposed system designed with two primary translation modules includes sign-to-text and text-to-sign. The sign-to-text module employs transfer learning models to translate Arabic sign images into text, while the text-to-sign module integrates a fuzzy string-matching tool to convert Arabic text into sign images. The system was customized using six CNN-based deep learning architectures: AlexNet, ResNet152V2, YOLOv8n, Swin Transformer, InceptionV3, and Xception. Additionally, the ArSL dataset and an Arabic data dictionary were employed to enhance the diversity, accuracy, and completeness of the selected CNN models, thereby improving the system's adaptability across various users and contexts. Experimental evaluations were conducted to assess the system's performance in terms of both accuracy and processing efficiency. The results demonstrated exceptionally high accuracy across all investigated CNN models, but YOLOv8n-cls demonstrated the highest accuracy with a score of 99.9%, followed by Xception, Swin Transformer, and AlexNet at 99.0%, and InceptionV3 and ResNet152V2 at 98.0%. These closely aligned results are attributed to the inherent characteristics of the dataset, as well as the shared methodologies employed, including preprocessing, data augmentation, cross-validation, and hyperparameter tuning. In terms of the real-time adaptability in recognizing each sign image, the InceptionV3, AlexNet, and YOLOv8n models

关键词： Sign language Accuracy Translation real-time systems deep learning Transformers Hands Data models Convolutional neural networks Computational modeling Arabic sign language hand gesture recognition transfer learning deep learning bidirectional sign translation two ways translations

来源：评论

学校读者我要写书评

暂无评论

Seeing Through the Haze: A Comprehensive Review of Underwater image Enhancement Techniques

引用

IEEE ACCESS 2024年 12卷 145206-145233页

作者： Saad Saoud, Lyes Elmezain, Mahmoud Sultan, Atif Heshmat, Mohamed Seneviratne, Lakmal Hussain, Irfan Khalifa Univ Khalifa Univ Ctr Autonomous Robot Syst Abu Dhabi U Arab Emirates

Underwater imaging suffers from significant quality degradation due to light scattering and absorption by water molecules, leading to color cast and reduced visibility. This hinders the ability to analyze and interpret the underwater world. image dehazing techniques have emerged as a crucial component for underwater image enhancement (UIE). This review comprehensively examines both traditional methods, rooted in the physics of light transmission in water, and recent advances in learning-based approaches, particularly deep learning architectures like Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and Transformers. We conduct a comparative analysis across various metrics, including visual quality, color fidelity, robustness to noise, and computational efficiency, to highlight the strengths and weaknesses of each approach. Furthermore, we address key challenges and future directions for traditional and learning-based methods, focusing on domain adaptation, real-time processing, and integrating physical priors into deep learning models. This review provides valuable insights and recommendations for researchers and practitioners in underwater image enhancement.

关键词： image color analysis image enhancement Sensitivity Reviews Colored noise image restoration Absorption Underwater navigation Underwater image enhancement traditional dehazing methods learning-based dehazing methods deep learning for underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing manufacturing process accuracy: A multidisciplinary approach integrating computer vision, machine learning, and control systems

引用

JOURNAL OF MANUFACTURING PROCESSES 2025年 142卷 453-467页

作者： Ramesh, Kaki Deshmukh, Sandip Ray, Tathagata Parimi, Chandu Birla Inst Sci & Technol Pilani Dept Mech Engn Hyderabad Campus Hyderabad 500078 Telangana India Birla Inst Sci & Technol Pilani Dept Comp Sci & Informat Syst Hyderabad Campus Hyderabad 500078 Telangana India Birla Inst Sci & Technol Pilani Dept Civil Engn Hyderabad Campus Hyderabad 500078 Telangana India

Manufacturing industries face significant challenges in producing high-quality, faultless products within limited timeframes. Conventional human-based inspection methods are still prone to errors and cannot guarantee precise component placement, potentially leading to product failures, user hazards, and substantial financial and reputational losses. This research presents a workflow to automate an inspection system that integrates computer vision, machine learning, image processing, and control systems to address these challenges. The proposed system employs a microcontroller and stepper motors to control a highly calibrated camera, enabling precise and efficient product inspection. At its core, the system utilizes the YOLOv5 model for object detection, specifically identifying hole marks and holes on products pre-assembly. This deep learning model was chosen for its real-time detection capabilities and high accuracy, achieving a mean Average Precision (mAP) of 0.95, which surpasses many current industry standards. Following object detection, advanced image processing techniques are applied to determine the precise position of detected features. Our approach achieves a notable error rate of 0.2 %, offering improvements over traditional inspection methods. Our system offers the potential to reduce inspection processing time and improve fault identification accuracy in real-time applications. Our research contributes to the field of industrial automation by introducing a seamless integration of state-of-the-art computer vision techniques with practical control systems. The system's modular design allows for easy adaptation to various manufacturing environments, benefiting industries with complex assembly processes, such as electronics, automotive manufacturing, etc. While the current implementation focuses on hole detection, future work will explore expanding the system's capabilities to identify a broader range of defects and adapt to different product types. This re

关键词： deep learning image processing Assembly Manufacturing industries Quality assurance

来源：评论

学校读者我要写书评

暂无评论

deep learning Innovations for Underwater Waste Detection: An In-Depth Analysis

引用

IEEE ACCESS 2025年 13卷 88917-88929页

作者： Walia, Jaskaran Singh Haridass, Kavietha Pavithra, L. K. Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India Vellore Inst Technol Ctr Human Movement Analyt Chennai 600127 India

Underwater waste detection is a critical challenge for preserving aquatic ecosystems, particularly due to inherent underwater distortions such as light refraction, occlusion, and scattering. In this study, we present a novel deep learning framework for real-time underwater waste detection by evaluating state-of-the-art object detection algorithms on a manually annotated custom dataset comprising images across various water bodies to represent real-world turbidity, illumination, and occlusion. Our approach incorporates robust feature extraction and specialized data augmentation techniques that effectively mitigate the adverse effects of underwater distortions. We investigate multiple architectures, including YOLOv8n, YOLOv7, YOLOv6s, YOLOv5s, Faster R-CNN, and Mask R-CNN, analyzing key parameters such as mean average precision (mAP), inference speed, and computational efficiency. Our results demonstrate that YOLO-based models achieve faster & accurate performance, with YOLOv8n and YOLOv7 reaching a detection accuracy of 96%, compared to 81% and 83% for Faster R-CNN and Mask R-CNN, respectively. Computationally, YOLOv8n achieves 76 ms (milliseconds) per frame, while YOLOv5s runs at 14 ms per frame, confirming real-time viability for AUV deployment. The proposed approach offers significant advantages over existing methods by enabling rapid, accurate detection with low computational overhead, thereby paving the way for integration with autonomous underwater vehicles (AUVs) for environmental monitoring and waste management.

关键词： deep learning Technological innovation Biological system modeling Robots Reviews Accuracy Lighting Benchmark testing YOLO Robot sensing systems Computer vision image processing robotics object detection underwater trash image segmentation deep learning CNN

来源：评论

学校读者我要写书评

暂无评论

deep learning-based framework for the observation of real-time melt pool and detection of anomaly in wire-arc additive manufacturing

引用

MATERIALS AND MANUFACTURING PROCESSES 2024年第6期39卷 761-777页

作者： Chandra, Mukesh Rajak, Sonu Vimal, K. E. K. Natl Inst Technol Patna Dept Mech Engn Patna India Natl Inst Technol Tiruchirappalli Dept Prod Engn Tiruchirappalli India Natl Inst Technol Patna Dept Mech Engn Patna 800005 India

Object detection has become a popular tool of deep learning in the era of digital manufacturing. In this study, the most powerful and efficient object detection algorithm, i.e., You Only Look Once (YOLO) algorithm, was used to detect anomalies in deposited beads of wire-arc additive manufacturing (WAAM) using melt pool images. This study used the latest version of YOLO algorithm to train and validate the custom image dataset of the melt pool obtained by conducting experiments using a robotic-controlled WAAM. The mean average precision (mAP) for the "Regular bead" class and the "Irregular bead" class reached 99% at an Intersection over Union (IoU) threshold of 0.5, for both training and validation. When the model was tested for new or unseen datasets by conducting four new experimental trials, the mAP value for the "Regular bead" class reached 98.47% and for the "Irregular bead" class reached 96.68% at an average processing time of 0.014 s/frame. The object detection algorithm YOLO has shown an excellent processing time of 15 ms per frame, which shows its potential for real-time application in the manufacturing industry.

关键词： WAAM deep learning object detection YOLOv8 real-time application

来源：评论

学校读者我要写书评

暂无评论

deep learning-based automatic defect detection of photovoltaic modules in infrared, electroluminescence, and red-green-blue images

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 332卷

作者： Lai, Yi-Sheng Hsieh, Chien-Chun Liao, Ting-Wei Huang, Chao-Yang Kuo, Chung-Feng Jeffrey Natl Taiwan Univ Sci & Technol Dept Mat Sci & Engn Taipei 10607 Taiwan Ind Technol Res Inst Green Energy & Environm Res Labs Hsinchu 310401 Taiwan

This study presents an automated defect detection system for photovoltaic modules that combines image processing techniques with deep learning models. The system identifies 21 types of defects using three imaging methods: infrared imaging, red-green-blue imaging, and electroluminescence imaging. Infrared imaging, captured using a thermal imager mounted on a drone, detects thermal anomalies such as hotspots and open circuits. red-green-blue imaging identifies surface-level defects, including glass breakage, soiling, and vegetation shading. Electroluminescence imaging, obtained with a charge-coupled device camera in a controlled darkroom environment, reveals internal defects such as microcracks, cell degradation, and busbar corrosion. Crossreferencing results from infrared and red-green-blue images facilitates the identification of defect causes, while electroluminescence imaging confirms internal issues and provides targeted recommendations for improvements. The system development was divided into four main stages. First, electroluminescence images were preprocessed and segmented using median filtering, thresholding, edge detection, and perspective correction techniques. Second, color features in infrared and red-green-blue images were enhanced through color space transformation to improve detection accuracy. Third, image datasets were augmented using rotation, flipping, and generative techniques to ensure model reliability. Finally, deep learning models were trained using transfer learning methods and optimized through cross-validation and hyperparameter tuning to achieve optimal performance for each imaging type. The proposed system demonstrates exceptional accuracy: 99.06% for thermal defect detection in infrared images, 100% for surface defect detection in red-green-blue images, and 99.2% for internal defect detection in electroluminescence images. The average processing time per image is less than 0.1 s, making the system suitable for real-time and large-scale p

关键词： Photovoltaic module Automated defect detection system Infrared image RGB image Electroluminescence image

来源：评论

学校读者我要写书评

暂无评论

Accelerating convolutional neural networks on FPGA platforms: a high-performance design methodology using OpenCL

引用

JOURNAL OF real-time image processing 2025年第2期22卷 1-19页

作者： Gdaim, Soufien Mtibaa, Abdellatif Sousse Univ Prince Res Lab ISITCOM Sousse Tunisia Univ Sfax Syst Integrat & Emerging Energies Lab Sfax Tunisia

Convolutional Neural Networks (CNNs) are among the most promising algorithms, outperforming traditional methods in classification tasks with superior accuracy. They have been widely applied across various deep learning domains, including computer vision, speech recognition, image processing, and object detection. However, many CNNs require substantial computational resources, particularly within their convolutional layers. As high-performance CNNs continue to evolve, their processing and memory requirements are also increasing. To address these challenges, this paper proposes an effective design methodology for accelerating CNN algorithms on Field-Programmable Gate Array (FPGA) hardware architectures. The proposed methodology introduces a novel approach for accelerating CNN algorithms using FPGAs, addressing the significant processing and memory demands associated with CNNs. The implementation is based on Open Computing Language (OpenCL), which provides rapid implementation flows. This approach was chosen for its efficiency in reducing development time and eliminating the need to manually write hardware description language (HDL) code. The MNIST and the CIFAR-10 datasets on the Xilinx ZYNQ 7000 device were used to evaluate our approach. Our method achieved a 97% recognition rate on MNIST and an 86% recognition rate on CIFAR-10. We compared the execution time of our accelerated CNN kernel on the FPGA with that of a single-core Central processing Unit (CPU). The experimental results demonstrate that our proposed design is 10 times faster than a standard CPU, validating its effectiveness. Our model optimizes power consumption and performance, exceeding previous studies in accuracy and efficiency. It is well suited for real-world applications that demand both precision and energy efficiency.

关键词： CNN Hardware accelerator FPGA OpenCL Machine learning Embedded system

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Mental Stress Using In-Ear Plethysmography and a Vision Transformer

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 4015-4027页

作者： Barki, Hika Nkenyereye, Lionel Chung, Wan-Young Pukyong Natl Univ Dept AI Convergence Busan 48513 South Korea Pukyong Natl Univ Dept Elect Engn Busan 48513 South Korea

This study addresses the critical need for effective mental stress monitoring, linked to severe health issues like depression and heart disease. We introduce a robust method using in-ear photoplethysmogram (PPG) signals for detecting and classifying stress levels. The objective of this study is to develop a precise stress monitoring technique using advanced signal processing and deep learning. Raw PPG data were collected from 15 subjects undergoing stress-inducing activities in a controlled setting. The data underwent preprocessing and were transformed into image-like time-frequency representations. We employed vision transformer (ViT) models for classification, which were fine-tuned and compared against other state-of-the-art deep learning models. The ViT classifier significantly outperformed existing models, achieving an average accuracy of 97.78% and an F1-score of 97.79%. While the dataset is relatively small, these results suggest a promising direction for stress monitoring by illustrating the potential of combining in-ear PPG signals with ViT models. The study indicates the efficacy of this novel approach for accurate mental stress diagnosis, which could have significant implications for mental health applications. Future work will focus on validating these findings with a larger sample size and exploring the integration of this technology into wearable devices for real-world stress monitoring.

关键词： Human factors Sensors Accuracy Monitoring Hardware Biomedical monitoring Heart rate variability Transformers real-time systems deep learning Classification filtering mental stress photoplethysmogram (PPG) time-frequency analysis vision transformer (ViT)

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：