检索结果-内蒙古大学图书馆

Space Imaging Point Source Detection and Characterization

IEEE ACCESS 2024年 12卷 90442-90460页

作者： Ribeiro, Francisco S. F. Garcia, Paulo J. V. Silva, Miguel Cardoso, Jaime S. Univ Porto Fac Engn P-4250465 Porto Portugal Inst Super Tecn CENTRA P-1049001 Lisbon Portugal INESC TEC P-4200465 Porto Portugal

Point source detection algorithms play a pivotal role across diverse applications, influencing fields such as astronomy, biomedical imaging, environmental monitoring, and beyond. This article reviews the algorithms used for space imaging applications from ground and space telescopes. The main difficulties in detection arise from the incomplete knowledge of the impulse function of the imaging system, which depends on the aperture, atmospheric turbulence (for ground-based telescopes), and other factors, some of which are time-dependent. Incomplete knowledge of the impulse function decreases the effectiveness of the algorithms. In recent years, deep learning techniques have been employed to mitigate this problem and have the potential to outperform more traditional approaches. The success of deep learning techniques in object detection has been observed in many fields, and recent developments can further improve the accuracy. However, deep learning methods are still in the early stages of adoption and are used less frequently than traditional approaches. In this review, we discuss the main challenges of point source detection, as well as the latest developments, covering both traditional and current deep learning methods. In addition, we present a comparison between the two approaches to better demonstrate the advantages of each methodology.

关键词： Noise measurement Detectors deep learning Apertures Signal to noise ratio Atmospheric measurements image processing Machine learning Object detection image annotation digital images high-resolution imaging machine learning object detection

来源：评论

学校读者我要写书评

暂无评论

A deep learning Model for Wafer Defect Map Classification: Perspective on Classification Performance and Computational Volume

引用

PHYSICA STATUS SOLIDI B-BASIC SOLID STATE PHYSICS 2024年第1期261卷 2300113-2300113页

作者： Kim, Minjoo Tak, Jinhyung Shin, Jitae Sungkyunkwan Univ Dept Semicond & Display Engn Suwon 16419 South Korea Samsung Elect Co Ltd Memory Div DRAM Prod Engn Team Hwaseong 18448 South Korea Sungkyunkwan Univ Dept Elect & Comp Engn Suwon 16419 South Korea

Wafer defect map images are generated by performing electrical tests on each chip on wafer. These images demonstrate specific failure patterns occurred from semiconductor manufacturing process. It is crucial for engineers to classify what kind of defect patterns on this wafer is early. In an attempt to automate the classification of wafer defect maps, which are currently manual dependent, various machine learning and deep learning models have been introduced. However, it has not been successfully applied to real-world mass production environments due to problems such as classification performance and computational volume. Therefore, the deep learning model integrating the Inception module and the skip connection module for wafer defect map classification is proposed here. This model has a fast training and inference speed with a small number of parameters, it is highly practical when processing large amounts of real-time test data in a semiconductor manufacturing environment because of its small computational volume and high classification performance. This method is applied on the real-field wafer test data, and the result shows that the proposed model takes a significant improvement on inference time by over 59% with high performance compared to the baseline model. This work presents a deep learning model integrating the Inception module and skip connection module for wafer defect map classification. This model shows fast training and inference speed with a small number of parameters and is highly practical in semiconductor manufacturing environment because of its small computational volume and high classification *** (c) 2023 WILEY-VCH GmbH

关键词： classification convolutional neural networks Inception module skip connection module wafer defect maps

来源：评论

学校读者我要写书评

暂无评论

Northern maize leaf blight disease detection and segmentation using deep convolution neural networks

引用

MULtimeDIA TOOLS AND APPLICATIONS 2024年第7期83卷 19415-19432页

作者： Rai, Chitranjan Kumar Pahuja, Roop Dr B R Ambedkar Natl Inst Technol Dept Instrumentat & Control Engn Jalandhar 144011 Punjab India

Maize is ranked as the third most important food crop in India after rice and wheat. The cultivation of this particular crop and its associated agricultural practices have faced many challenges over the centuries. Maize is susceptible to Northern Leaf Blight (NLB), a highly contagious fungal foliar disease. The primary reason for the reduction in yield resulting from NLB is the loss of photosynthetic leaf area. Therefore, identifying diseases at an early stage is critical to ensure that the treatment process is carried out correctly and that the quality of results is maintained. This research uses a deep learning-based Attention U-Net model to explore a real-time, effective approach for segmentation and detecting NLB diseases in maize crops. Data augmentation is performed after image annotation to increase the model's effectiveness, and the model is trained from scratch. The model was trained for a maximum of 50 epochs using an initial learning rate of 0.0001 with Adam as an optimizer, and its performance was tested on the test dataset. This study shows that the Attention U-Net model outperformed other image segmentation methods, such as Res U-Net and Plain U-Net, and showed better results with an Intersection over Union (IoU) of 72.41%, 70.91% and 51.95%, respectively. The proposed model achieves an average pixel-wise F1 score of 85.23%. The diseased segmentation accuracy clenched to 98.97%, and the Dice coefficient (DC) of disease spot segmentation is 81.39%. Adding an attention mechanism to the U-Net architecture improves its ability to express local features, resulting in improved NLB disease image segmentation performance.

关键词： Attention U-Net deep learning Plant segmentation Maize real-time

来源：评论

学校读者我要写书评

暂无评论

real-time masked face recognition using deep learning-based double generator network

引用

SIGNAL image AND VIDEO processing 2024年第SUPPL 1期18卷 325-334页

作者： Sumathy, G. Usha, M. Rajakumar, S. Jayapriya, P. SRM Inst Sci & Technol Dept Computat Intelligence Chennai 603203 Tamil Nadu India MEASI Inst Informat Technol Dept Masters Comp Applicat Chennai Tamilnadu India Panimalar Engn Coll Dept Elect & Commun Engn Chennai 600123 India Sri Eshwar Engn Coll Ctr Future Networks & Digital Twin Dept Comp Sci & Engn Coimbatore India

The COVID-19 outbreak has spread rapidly worldwide since 2019. This pandemic has complicated and intricate human existence, and thousands have died from it. Due to the spread of coronavirus, people wear masks while going outside. Consequently, the system cannot identify their faces while wearing the masks. This issue can be overcome by introducing a system that recognizes masked faces of random people trained with 100 images taken from the Internet. This paper presents a novel deep learning-based double generator network to precisely identify the face behind the mask images. Initially, the gathered images are split into low- and high-frequency components using 2D-stationary wavelet transform (2D-SWT). Afterward, the Haar cascade classifier was implemented to capture the masked image biometrics to recognize the individual faces. The proposed double generator network involves two modules: edge generation and image reconstruction. The first modules consist of dilated convolutional for retrieving the relevant features from the masked face images created on the generated edges. The generated edges are reconstructed using the reflection of generated edges in the second module. Finally, the output images are reconstructed to identify the masked face. From the simulation results, the proposed framework showed effective performance based on the network parameters. The proposed network attains an accuracy of 97.08% for masked face recognition which demonstrates it achieves higher accuracy than the prior frameworks.

关键词： Masked face recognition deep learning Stationary wavelet transform Haar cascade classifier Double generator network

来源：评论

学校读者我要写书评

暂无评论

PhenoNet: A two-stage lightweight deep learning framework for real-time wheat phenophase classification

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2024年 208卷 136-157页

作者： Zhang, Ruinan Jin, Shichao Zhang, Yuanhao Zang, Jingrong Wang, Yu Li, Qing Sun, Zhuangzhuang Wang, Xiao Zhou, Qin Cai, Jian Xu, Shan Su, Yanjun Wu, Jin Jiang, Dong Nanjing Agr Univ Acad Adv Interdisciplinary Studies Plant Phen Res CtrCollaborat Innovat Ctr Modern C Coll AgrState Key Lab Crop Genet & Germplasm Enha Nanjing 210095 Peoples R China Chinese Acad Sci Inst Bot State Key Lab Vegetat & Environm Change Beijing 100093 Peoples R China Univ Hong Kong Inst Climate & Carbon Neutral Sch Biol Sci Pokfulam Rd Hong Kong Peoples R China

The real-time monitoring of wheat phenology variations among different varieties and their adaptive responses to environmental conditions is essential for advancing breeding efforts and improving cultivation management. Many remote sensing efforts have been made to relieve the challenges of key phenophase detection. However, existing solutions are not accurate enough to discriminate adjacent phenophases with subtle organ changes, and they are not real-time, such as the vegetation index curve -based methods relying on entire growth stage data after the experiment was finished. Furthermore, it is key to improving the efficiency, scalability, and availability of phenological studies. This study proposes a two -stage deep learning framework called PhenoNet for the accurate, efficient, and real-time classification of key wheat phenophases. PhenoNet comprises a lightweight encoder module (PhenoViT) and a long short-term memory (LSTM) module. The performance of PhenoNet was assessed using a well -labeled, multi -variety, and large -volume dataset (WheatPheno). The results show that PhenoNet achieved an overall accuracy (OA) of 0.945, kappa coefficients (Kappa) of 0.928, and F1 -score (F1) of 0.941. Additionally, the network parameters (Params), number of operations measured by multiply -adds (MAdds), and graphics processing unit memory required for classification (Memory) were 0.889 million (M), 0.093 Giga times (G), and 8.0 Megabytes (MB), respectively. PhenoNet outperformed eleven state-of-the-art deep learning networks, achieving an average improvement of 3.7% in OA, 5.1% in Kappa, and 4.1% in F1, while reducing average Params, MAdds, and Memory by 78.4%, 85.0%, and 75.1%, respectively. The feature visualization and ablation analysis explained that PhenoNet mainly benefited from using time -series information and lightweight modules. Furthermore, PhenoNet can be effectively transferred across years, achieving a high OA of 0.981 using a two -stage transfer learning strat

关键词： Wheat phenology Dataset image classification deep learning Transfer learning Web application

来源：评论

学校读者我要写书评

暂无评论

Overcoming annotation bottlenecks in underwater fish segmentation: a robust self-supervised learning approach

引用

SIGNAL image AND VIDEO processing 2025年第4期19卷 1-10页

作者： Saleh, Alzayat Sheaves, Marcus Jerry, Dean Azghadi, Mostafa Rahimi James Cook Univ Coll Sci & Engn Townsville Qld Australia James Cook Univ ARC Res Hub Supercharging Trop Aquaculture Genet S Townsville Qld Australia

Accurate fish segmentation in underwater videos is challenging due to low visibility, variable lighting, and dynamic backgrounds, making fully-supervised methods that require manual annotation impractical for many applications. This paper introduces a novel self-supervised learning approach for fish segmentation using deep learning. Our model, trained without manual annotation, learns robust and generalizable representations by aligning features across augmented views and enforcing spatial-temporal consistency. We demonstrate its effectiveness on three challenging underwater video datasets: deepFish, Seagrass, and YouTube-VOS, surpassing existing self-supervised methods and achieving segmentation accuracy comparable to fully-supervised methods without the need for costly annotations. Trained on deepFish, our model exhibits strong generalization, achieving high segmentation accuracy on the unseen Seagrass and YouTube-VOS datasets. Furthermore, our model is computationally efficient due to its parallel processing and efficient anchor sampling technique, making it suitable for real-time applications and potential deployment on edge devices. We present quantitative results using Jaccard Index and Dice coefficient, as well as qualitative comparisons, showcasing the accuracy, robustness, and efficiency of our approach for advancing underwater video analysis.

关键词： Computer vision Convolutional neural networks Underwater videos deep learning Transformer Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Target recognition in diverse synthetic aperture radar image datasets with low size weight and power processing hardware

引用

IET RADAR SONAR AND NAVIGATION 2024年第11期18卷 2066-2076页

作者： Lane, Richard O. Holmes, Wendy J. Lamont-Smith, Timothy QinetiQ St Andrews Rd Great Malvern WR14 3PS England

This paper studies the performance of target detection and classification algorithms applied to synthetic aperture radar (SAR) data. We describe a process to merge measured environmental SAR scene images with target image chips to produce a large dataset for training deep learning algorithms. Three algorithms, RetinaNet, EfficientDet, and YOLOv5, were trained using a powerful cloud server. Performance at inference time, in terms of speed and accuracy, was tested on both the cloud server and a low size weight and power (SWAP) single board computer. YOLOv5 was found to be the most accurate and fastest algorithm on the cloud server but the slowest on the low-SWAP device. RetinaNet and EfficientDet produced operationally useful throughput on the low-SWAP device for surveillance applications, with RetinaNet having the higher accuracy. Further qualitative analysis of algorithm performance on additional data with different characteristics highlighted the importance of gathering relevant training data and carrying out suitable pre-processing steps. This paper studies deep learning based target detection and classification algorithms applied to synthetic aperture radar data where environmental images are merged with target image chips to produce a large training dataset. Speed and accuracy performance at inference time is tested on a cloud server and low size weight and power single board computer. Qualitative analysis of algorithm performance on additional data with different characteristics highlights the importance of gathering relevant training data and carrying out suitable pre-processing steps. image

关键词： artificial intelligence convolutional neural nets learning (artificial intelligence) neural nets object detection radar target recognition synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

time-Series to image-Transformed Adversarial Autoencoder for Anomaly Detection

引用

IEEE ACCESS 2024年 12卷 119671-119684页

作者： Kang, Jiyoung Kim, Minseok Park, Jinuk Park, Sanghyun Samsung Elect IP Prosecut Team Seoul 06765 South Korea Yonsei Univ Dept Comp Sci Seoul 03722 South Korea

The automation of systems and the accelerated digital transformations across various industries have rendered the manual monitoring of systems difficult. Therefore, the automatic detection of system anomalies is essential in diverse industries. Various deep learning-based techniques have been developed for anomaly detection in multivariate time-series data with promising performance. However, there are several challenges: 1) difficulty in understanding the relationships among time-series data due to their complexity and high-dimensionality, 2) limitation in distinguishing anomalies from normal data that exhibit similar distributional patterns, and 3) lack of intuitive interpretation of anomaly detection results. To address these issues, we propose a novel approach referred to as the time-series to image-transformed adversarial autoencoder (T2IAE), which adopts image transformation techniques and convolutional neural network (CNN)-based adversarial learning. image transformation techniques were used to effectively capture the local features of adjacent time points. Two CNN-based adversarial autoencoders competitively learned to distinguish between normal and abnormal data. We experimentally analyzed five real-world multivariate time-series datasets, wherein the proposed model achieved superior anomaly detection performance compared with state-of-the-art methods. Moreover, the proposed model enables humans to intuitively interpret the detection results, facilitating appropriate explanations of the results and enhancing the model's usability.

关键词： Data models Anomaly detection time series analysis Computational modeling Adversarial machine learning image transformation Computational efficiency Unsupervised learning Multivariate regression unsupervised learning multivariate time-series data image transformation

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

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

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：