检索结果-内蒙古大学图书馆

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

real-time Human Activity Recognition using Wi-Fi CSI: A deep CNN Architecture Approach 13

Real-Time Human Activity Recognition using Wi-Fi CSI: A Deep...

引用

13th International Conference on image processing Theory Tools and Applications

作者： Karim, Meridja Imene, Sekkiou Aymen, Gammoudi Univ Paris Saclay Campus Evry Evry France Caplogy Velizy Villacoublay France

ISBN: (纸本)9798331541859;9798331541842

Human activity recognition (HAR) using Wi-Fi signals has gained significant attention due to its non-invasive nature, ubiquity, and respect for privacy, in contrast to camera-based systems. This study aims to develop a robust deep learning model for real-time HAR using Channel State Information (CSI) from Wi-Fi signals. We propose a deep Convolutional Neural Network (CNN) architecture incorporating an attention mechanism to process CSI data and classify various human activities. Our model was trained and tested using a comprehensive dataset of Wi-Fi CSI, employing advanced data augmentation techniques to enhance model generalization. The proposed model achieved an impressive accuracy of 99.69%, significantly outperforming existing approaches in terms of precision, recall, and F1 score. These findings demonstrate the potential of using Wi-Fi CSI with deep CNNs and attention mechanisms for accurate and real-time HAR, paving the way for applications in smart homes, healthcare monitoring, and other domains requiring efficient and privacy-preserving activity recognition. Future work will explore adapting this methodology to a variety of datasets and integrating an emotion recognition system to further expand its capabilities.

关键词： human activity recognition (HAR) Wi-Fi sensing deep learning attention mechanism channel state information(CSI) Convolutional neural network (CNN) Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional image reconstruction of opaque particle swarms by lightweight dual-residual deep learning computed tomography

引用

OPTICS COMMUNICATIONS 2024年 554卷

作者： Shi, Yue Ou, Pan Zheng, Ming Wu, Jian Beihang Univ Sch Phys Beijing 100191 Peoples R China Beihang Univ Sch Instrumentat & Optoelect Engn Beijing 100191 Peoples R China

High quality of three-dimensional particle swarm images is always highly desired in some important areas like experimental fluid mechanics and combustion field measurement, etc. as particle distributions in these fields can characterize the field properties well. Recently, deep learning techniques have been applied for the computed tomography to improve three-dimensional image reconstruction quality of an object. However, how to promote the network processing efficiency and quality to reduce artifact noise, missing-particles and ghost-particles in the reconstruction image is still a challenge at present. For this purpose, we propose a lightweight dual-residual deep learning approach for improvement of tomographic image reconstruction of particle swarms in this paper. It includes the innovative designs in lightweight dual-residual down-sampling, fast feature convergence module and high-SNR network input datasets to acquire image features more effectively. Numerical analysis and experimental test have demonstrated that the proposed method can effectively reduce not only the missing particles and ghost-particles in the reconstructed images under sparse-sampling, but also the network training time, in contrast to the performances of some typical deep learning networks under the same conditions.

关键词： Computed tomography deep learning Three-dimensional image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Research Review and Perspective Toward Plant Leaf Disease Detection Using image processing Techniques

引用

INTERNATIONAL JOURNAL OF image AND GRAPHICS 2024年第0期

作者： Kindalkar, Amrita Arjun Srinivas Univ Mangalore 574146 Karnataka India

Plant Leaf Disease (PLD) detection is helpful for several fields like Agriculture Institute and Biological Research. The country's economic growth depends on the productivity of the agricultural field. Recently developed models based on deep learning give more accurate and precise results over the detection and classification of PLD while evolving through image processing approaches. Many image-processing approaches are used for the identification and classification of PLD. The quality of agricultural products is mainly affected by several factors like fungi, bacteria, and viruses. These factors severely destroy the entire growth of the plant. Hence, some outperformed models are needed to detect and identify the severity level of plant diseases yet, the identification requires more time and has a struggle to identify the appropriate type of disease based on its symptoms. Therefore, several automatic detection and classification models are developed to avoid the time complexity. Computerized image processing approaches are utilized for crop protection, which analyzes the color information of leaves from the collected images. Hence, image processing techniques play an important role in the identification and classification of PLD. It gives more advantages by lowering the task of illustrating crops on large farms and detecting the leaf diseases at the initial stage itself based on the symptoms of the plant leaves. While implementing a new model, there is a need to study various machine and deep learning-based structures for PLD detection approaches. This research work provides an overview of various heuristic approaches, machine learning, and deep learning models for the detection and classification of PLD. This research work also covers the various constraints like PLD detection tools, performance measures, datasets used, and chronological review. Finally, the research work explores the research findings and also the research gaps with future scope.

关键词： Plant leaf diseases leaf images image processing approaches deep learning algorithms machine learning algorithms performance measures research gaps utilization of tools used datasets

来源：评论

学校读者我要写书评

暂无评论

learning mapping by curve iteration estimation For real-time underwater image enhancement

引用

OPTICS EXPRESS 2024年第6期32卷 9931-9945页

作者： Wang, Junting Ye, Xiufen Liu, Yusong Mei, Xinkui Wei, Xing Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China Harbin Med Univ Sch Interdisciplinary Med & Engn Harbin 150081 Peoples R China

The degradation and attenuation of light in underwater images impose constraints on underwater vision tasks. However, the complexity and the low real-time performance of most current image enhancement algorithms make them challenging in practical applications. To address the above issues, we propose a new lightweight framework for underwater image enhancement. We adopt the curve estimation to learn the mapping between images rather than end -to -end networks, which greatly reduces the requirement for computing resources. Firstly, a designed iterative curve with parameters is used to simulate the mapping from the raw to the enhanced image. Then, the parameters of this curve are learned with a parameter estimation network called CieNet and a set of loss functions. Experimental results demonstrate that our proposed method is superior to existing algorithms in terms of evaluating indexes and visual perception quality. Furthermore, our highly lightweight network enables it to be easily integrated into small devices, making it highly applicable. The extremely short running -time of our method facilitates real-time underwater image enhancement.

关键词： deep learning image enhancement image metrics Imaging techniques real time imaging Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in real-time Video Surveillance: A deep learning-Based Remedial Approach for Adversarial Attack Mitigation

引用

IEEE ACCESS 2024年 12卷 88913-88926页

作者： Ranjana Panigrahi, Gyana Kumar Sethy, Prabira Kumari Behera, Santi Gupta, Manoj Alenizi, Farhan A. Nanthaamornphong, Aziz Sambalpur Univ Dept Elect Sambalpur 768019 Orissa India Guru Ghasidas Vishwavidyalaya Dept Elect & Commun Engn Bilaspur 495009 Chhattisgarh India VSSUT Dept CSE Burla 768018 India Guru Ghasidas Vishwavidyalaya SOS Engn & Technol Dept Informat Technol Bilaspur 495009 Chhattisgarh India Prince Sattam bin Abdulaziz Univ Coll Engn Dept Elect Engn Al Kharj 11942 Saudi Arabia Prince Songkla Univ Coll Comp Phuket 83120 Thailand

This paper introduces an innovative methodology to disrupt deep-learning (DL) surveillance systems by implementing an adversarial framework strategy, inducing misclassification in live video objects and extending attacks to real-time models. Focusing on the vulnerability of image-categorization models, the study evaluates the effectiveness of face mask surveillance against adversarial threats. A real-time system, employing the ShuffleNet V1 transfer-learning algorithm, was trained on a Kaggle dataset for face mask detection accuracy. Using a white-box Fast Gradient Sign Method (FGSM) attack with epsilon at 0.13, the study successfully generated adversarial frames, deceiving the face mask detection system and prompting unintended video predictions. The findings highlight the risks posed by adversarial attacks on critical video surveillance systems, specifically those designed for face mask detection. The paper emphasizes the need for proactive measures to safeguard these systems before real-world deployment, crucial for ensuring their robustness and reliability in the face of potential adversarial threats.

关键词： Face recognition Streaming media real-time systems Data models Computational modeling Perturbation methods Adversarial machine learning Video surveillance Adversarial attacks deep learning face mask recognition video surveillance systems face mask detection ShuffleNetV1

来源：评论

学校读者我要写书评

暂无评论

deep learning with uncertainty estimation for automatic tumor segmentation in PET/CT of head and neck cancers: impact of model complexity, image processing and augmentation

引用

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS 2024年第5期10卷 055038-055038页

作者： Huynh, Bao Ngoc Groendahl, Aurora Rosvoll Tomic, Oliver Liland, Kristian Hovde Knudtsen, Ingerid Skjei Hoebers, Frank van Elmpt, Wouter Dale, Einar Malinen, Eirik Futsaether, Cecilia Marie Norwegian Univ Life Sci Fac Sci & Technol As Norway Vestre Viken Hosp Trust Sect Oncol Drammen Norway Norwegian Univ Sci & Technol Dept Circulat & Med Imaging Trondheim Norway GROW Sch Oncol & Reprod Dept Radiat Oncol MAASTRO Maastricht Netherlands Oslo Univ Hosp Dept Oncol Oslo Norway Oslo Univ Hosp Dept Med Phys Oslo Norway Univ Oslo Dept Phys Oslo Norway Vestre Viken Hosp Trust Drammen Norway

Objective. Target volumes for radiotherapy are usually contoured manually, which can be time-consuming and prone to inter- and intra-observer variability. Automatic contouring by convolutional neural networks (CNN) can be fast and consistent but may produce unrealistic contours or miss relevant structures. We evaluate approaches for increasing the quality and assessing the uncertainty of CNN-generated contours of head and neck cancers with PET/CT as input. Approach. Two patient cohorts with head and neck squamous cell carcinoma and baseline 18F-fluorodeoxyglucose positron emission tomography and computed tomography images (FDG-PET/CT) were collected retrospectively from two centers. The union of manual contours of the gross primary tumor and involved nodes was used to train CNN models for generating automatic contours. The impact of image preprocessing, image augmentation, transfer learning and CNN complexity, architecture, and dimension (2D or 3D) on model performance and generalizability across centers was evaluated. A Monte Carlo dropout technique was used to quantify and visualize the uncertainty of the automatic contours. Main results. CNN models provided contours with good overlap with the manually contoured ground truth (median Dice Similarity Coefficient: 0.75-0.77), consistent with reported inter-observer variations and previous auto-contouring studies. image augmentation and model dimension, rather than model complexity, architecture, or advanced image preprocessing, had the largest impact on model performance and cross-center generalizability. Transfer learning on a limited number of patients from a separate center increased model generalizability without decreasing model performance on the original training cohort. High model uncertainty was associated with false positive and false negative voxels as well as low Dice coefficients. Significance. High quality automatic contours can be obtained using deep learning architectures that are not overly complex.

关键词： head and neck cancers GTV auto-segmentation deep learning contour uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

deep learning-Based Assessment Model for real-time Identification of Visual Learners Using Raw EEG

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2024年 32卷 378-390页

作者： Jawed, Soyiba Faye, Ibrahima Malik, Aamir Saeed Brno Univ Technol Fac Informat Technol Brno 60167 Czech Republic Univ Teknol PETRONAS Ctr Intelligent Signal & Imaging Res CISIR Dept Fundamental & Appl Sci Seri Iskandar 32610 Malaysia Brno Univ Technol Fac Informat Technol Dept Comp Syst Brno 60167 Czech Republic

Automatic identification of visual learning style in real time using raw electroencephalogram (EEG) is challenging. In this work, inspired by the powerful abilities of deep learning techniques, deep learning-based models are proposed to learn high-level feature representation for EEG visual learning identification. Existing computer-aided systems that use electroencephalograms and machine learning can reasonably assess learning styles. Despite their potential, offline processing is often necessary to eliminate artifacts and extract features, making these methods unsuitable for real-time applications. The dataset was chosen with 34 healthy subjects to measure their EEG signals during resting states (eyes open and eyes closed) and while performing learning tasks. The subjects displayed no prior knowledge of the animated educational content presented in video format. The paper presents an analysis of EEG signals measured during a resting state with closed eyes using three deep learning techniques: Long-term, short-term memory (LSTM), Long-term, short-term memory-convolutional neural network (LSTM-CNN), and Long-term, short-term memory-Fully convolutional neural network (LSTM-FCNN). The chosen techniques were based on their suitability for real-time applications with varying data lengths and the need for less computational time. The optimization of hypertuning parameters has enabled the identification of visual learners through the implementation of three techniques. LSTM-CNN technique has the highest average accuracy of 94%, a sensitivity of 80%, a specificity of 92%, and an F1 score of 94% when identifying the visual learning style of the student out of all three techniques. This research has shown that the most effective method is the deep learning-based LSTM-CNN technique, which accurately identifies a student's visual learning style.

关键词： Raw-electroencephalogram deep learning machine learning visual learner classification learning styles

来源：评论

学校读者我要写书评

暂无评论

deep learning based authentication schemes for smart devices in different modalities: progress, challenges, performance, datasets and future directions

引用

MULtimeDIA TOOLS AND APPLICATIONS 2024年第28期83卷 71451-71493页

作者： Shende, Shailendra W. Tembhurne, Jitendra V. Ansari, Nishat Afshan Indian Inst Informat Technol Nagpur 441108 India Govt Coll Engn Chandrapur 442403 India

deep learning algorithms have shown exceptional effectiveness in a wide range of supervised and unsupervised learning tasks in a variety of fields, including image processing, computer vision, natural language processing, and speech or voice processing. In this paper, a comprehensive analysis is conducted to assess the impact of deep learning on user authentication using both physiological and behavioural biometrics. This work encompasses the diverse deep learning approaches employed in authentication schemes tailored for smart devices. Meticulous scrutiny of commonly used datasets in these authentication studies is undertaken, accompanied by a comparative assessment of performance. The deep learning models under consideration span a spectrum of architectures, including deep neural networks, convolutional neural networks, deep auto-encoders, recurrent neural networks, and their variants. To enhance the clarity and categorization of authentication techniques for smart devices, a taxonomy is proposed based on the specific authentication metrics employed: (1) Knowledge-based Authentication (KBA), (2) Physiological Biometric-based Authentication (PBBA), (3) Behavioural Biometric-based Authentication (BBBA), (4) Physiological and Behavioural Continuous Authentication (PBBCA), and (5) Multi Modal Authentication (MMA). Furthermore, potential contributions of deep learning techniques to the realms of physiological and behavioural biometrics are discussed. Significance is placed on performance metrics, including accuracy, stability, and robustness, in evaluating these deep learning-based authentication systems. The challenges and limitations that deep learning approaches must surmount when dealing with real-world biometric data in the context of biometric identification systems are examined. This work not only underscores the transformative role of deep learning in user authentication but also offers valuable insights into the evolving landscape of biometric identification o

关键词： deep learning CNN RNN Authentication Biometrics Smart devices

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：