检索结果-内蒙古大学图书馆

Hologram Noise Model for Data Augmentation and deep learning

SENSORS 2024年第3期24卷 948页

作者： Terbe, Daniel Orzo, Laszlo Bicsak, Barbara Zarandy, Akos HUN REN Inst Comp Sci & Control SZTAK H-1111 Budapest Hungary

This paper introduces a noise augmentation technique designed to enhance the robustness of state-of-the-art (SOTA) deep learning models against degraded image quality, a common challenge in long-term recording systems. Our method, demonstrated through the classification of digital holographic images, utilizes a novel approach to synthesize and apply random colored noise, addressing the typically encountered correlated noise patterns in such images. Empirical results show that our technique not only maintains classification accuracy in high-quality images but also significantly improves it when given noisy inputs without increasing the training time. This advancement demonstrates the potential of our approach for augmenting data for deep learning models to perform effectively in production under varied and suboptimal conditions.

关键词： deep learning neural networks CNN noise modeling image augmentation image processing hologram

来源：评论

学校读者我要写书评

暂无评论

Age-based clustering of seagrass blades using AI models

Age-based clustering of seagrass blades using AI models

引用

Conference on real-time image processing and deep learning

作者： Sevinc, Omer Mehrubeoglu, Mehrube Cammarata, Kirk Huang, Chi McLauchlan, Lifford Texas A&M Univ Dept Engn Corpus Christi TX 78412 USA Texas A&M Univ Dept Life Sci Corpus Christi TX 78412 USA Texas A&M Univ Dept Elect Engn & Comp Sci Kingsville TX USA

ISBN: (纸本)9781510673878;9781510673861

Seagrass ecosystems play a vital role in maintaining marine biodiversity and ecological balance, making their monitoring and management essential. This study proposes a novel approach for clustering of seagrass images into three distinct age categories: young, medium, and old, using deep learning and unsupervised machine learning techniques. VGG-16 convolutional neural networks (CNN) are employed for feature extraction from the seagrass images, followed by K-means clustering to categorize the image samples into the specified age groups. The implemented methodology begins with the collection and annotation of a diverse seagrass image dataset, including samples from various locations and conditions. images are first pre-processed to ensure consistent size and quality. To enable real-time capabilities, an optimized VGG-16 CNN is then fine-tuned on the annotated dataset to learn discriminative features that capture age-related characteristics of the seagrass leaves within the constraints of real-time image processing. After feature extraction, the K-means clustering algorithm is applied to group the images into young, medium, and old categories based on the learned features. The clustering results are evaluated using quantitative metrics such as the silhouette score and Davies-Bouldin index, demonstrating the effectiveness of the proposed method in capturing age-related patterns in seagrass imagery. This research contributes to the field of seagrass monitoring by providing an automated and real-time approach to classifying seagrass images into age categories which can facilitate more accurate assessments of seagrass health and growth dynamics. A real-time capability would equip decision-makers with a valuable tool for immediate responses and support the sustainable management of seagrass ecosystems in various marine environments.

关键词： deep learning machine learning K-means clustering VGG-16 CNN seagrass age classification transfer learning ecosystem monitoring

来源：评论

学校读者我要写书评

暂无评论

Neural-network based high-speed volumetric dynamic optical coherence tomography

引用

BIOMEDICAL OPTICS EXPRESS 2024年第5期15卷 3216-3239页

作者： Liu, Yusong Abd El-Sadek, Ibrahim Morishita, Rion Makita, Shuichi Mori, Tomoko Furukawa, Atsuko Matsusaka, Satoshi Yasuno, Yoshiaki Univ Tsukuba Computat Opt Grp 1-1-1 Tennodai Tsukuba Ibaraki 3058573 Japan Damietta Univ Fac Sci Dept Phys Dumyat 34517 Egypt Univ Tsukuba Fac Med Clin Res & Reg Innovat Tsukuba Ibaraki 3058575 Japan

We demonstrate deep -learning neural network (NN) -based dynamic optical coherence tomography (DOCT), which generates high -quality logarithmic -intensity -variance (LIV) DOCT images from only four OCT frames. The NN model is trained for tumor spheroid samples using a customized loss function: the weighted mean absolute error. This loss function enables highly accurate LIV image generation. The fidelity of the generated LIV images to the ground truth LIV images generated using 32 OCT frames is examined via subjective image observation and statistical analysis of image -based metrics. Fast volumetric DOCT imaging with an acquisition time of 6.55 s/volume is demonstrated using this NN -based method.

关键词： deep learning image metrics Neural networks Optical coherence tomography real time imaging Signal processing

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning and Transformer for Fast Magnetic Resonance Imaging Scan

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2024年第3期8卷 2310-2323页

作者： Liu, Yiming Pang, Yanwei Jin, Ruiqi Hou, Yonghong Li, Xuelong Tianjin Univ Sch Elect & Informat Engn Tianjin Key Lab Brain Inspired Intelligence Techno Tianjin 300072 Peoples R China Tiandatz Technol Co Ltd Tianjin 301723 Peoples R China China Telecom Corp Ltd Inst Artificial Intelligence TeleAI Beijing 100033 Peoples R China

A major drawback in Magnetic Resonance Imaging (MRI) is the long scan times necessary to acquire complete K-space matrices using phase encoding. This paper proposes a transformer-based deep Reinforcement learning (RL) framework (called TITLE) to reduce the scan time by sequentially selecting partial phases in real-time so that a slice can be accurately reconstructed from the resultant slice-specific incomplete K-space matrix. As a deep learning based slice-specific method, the TITLE method has the following characteristic and merits: (1) It is real-time because the decision of which phase to be encoded in next time can be made within the period between the time at which an echo signal is obtained and the time at which the next 180(degrees )RF pulse is activated. (2) It exploits the powerful feature representation ability of transformer, a self-attention based neural network, for predicting phases with the mechanism of deep reinforcement learning. (3) Both historically selected phases (called phase-indicator vector) and the corresponding undersampled image of the slice being scanned are used for extracting features by transformer. Experimental results on the fastMRI dataset demonstrate that the proposed method is 150 times faster than the state-of-the-art reinforcement learning based method and outperforms the state-of-the-art deep learning based methods in reconstruction accuracy. The source codes are available.

关键词： image reconstruction Transformers Reinforcement learning Magnetic resonance imaging Iron Feature extraction Encoding Scan trajectory fast MRI deep reinforcement learning magnetic resonance imaging transformer

来源：评论

学校读者我要写书评

暂无评论

Dynamic Tactical image Recognition and Analysis in Football Matches Using Convolutional Neural Networks

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 583-592页

作者： Xie, Qi Baoji Univ Arts & Sci Sch Phys Educ Baoji 721000 Peoples R China

With the increasing complexity of modern football tactics, how to intelligently and accurately analyze tactical changes in real-time during matches has become an important research direction. Traditional manual tactical analysis methods are inefficient and susceptible to subjective bias. Therefore, using computer vision and deep learning technologies for tactical image recognition and analysis in football matches has gradually become a research hotspot. Convolutional Neural Networks (CNNs), as a powerful image processing tool, have been widely applied in video analysis and player detection. However, multi-target motion prediction and tracking management in dynamic football match scenes still face significant challenges. Existing research mainly focuses on static image analysis or simple player tracking, but the high-frequency image updates, player interactions, and occlusion issues in football matches complicate multi-target tracking. While some deep learning-based methods for multi-target detection and tracking have made progress, challenges remain, such as handling high-density player targets and improving motion trajectory prediction accuracy. To address these shortcomings, this study proposes two core techniques based on CNNs: first, multi-target motion prediction, which accurately forecasts players' future positions based on historical motion data;second, multi-target tracking management, which uses deep learning to track and manage each player's movement trajectory in real-time. Through these two techniques, this research aims to improve the realtime and accuracy of tactical analysis in football matches, providing coaches and analysts with more scientific and efficient tactical decision-making support.

关键词： CNN football matches dynamic tactical image multi-target motion prediction multi-target tracking management computer vision

来源：评论

学校读者我要写书评

暂无评论

A Hardware Architecture Design for High-Speed Vessel Orientation Recognition

引用

IEEE ACCESS 2024年 12卷 155287-155294页

作者： Han, Dongjun Xu, Ming Wu, Yuhang Zhou, Fuhui Nanjing Univ Aeronaut & Astronaut Dept Elect & Informat Engn Nanjing Jiangsu Peoples R China

Vascular orientation recognition (VOR) holds widespread applications in biomedical domains such as vascular image processing. Although many methods based on deep learning (DL) running on CPUs have been proposed and achieved appreciable results, they encounter a speed bottleneck. Therefore, an FPGA-based hardware design scheme is proposed in this paper to achieve high-speed VOR using small circuits. The design employs a streaming processing method for image thresholding and replaces static lookup tables (LUT) with the CORDIC algorithm to reduce resource consumption. Additionally, further compression of the angle mapping range is employed to achieve superior hardware resource optimization. Compared to purely software solutions, experimental results obtained with the simulated and actual vascular images demonstrate a 12.9x computational acceleration employing the proposed scheme. Moreover, the proposed scheme, in contrast to hardware implementations based on Lookup Table and Function Approximation, reduces LUT resource consumption by over 60%. Compared with two previous CORDIC algorithm studies, the proposed algorithm achieves a 14.6% and 20.5% reduction in LUT resource usage, thus showing enormous potential in real-time medical devices for tracking and computation of main vascular trajectory.

关键词： Hardware real-time systems Field programmable gate arrays Computer architecture image analysis Approximation algorithms Optimization image edge detection Feature extraction Accuracy Biomedical monitoring Circulatory system Medical image processing vascular orientation recognition improved CORDIC algorithm

来源：评论

学校读者我要写书评

暂无评论

Contraband detection of millimeter wave image for postal security checks using a spatial transformer-feature fusion network

引用

APPLIED OPTICS 2024年第18期63卷 4868-4873页

作者： Xu, Li -Min Pan, Zi-Xiang Wu, Heng Di, Jiang-Lei Qin, Yu-Wen Guangdong Univ Technol Adv Inst Photon Technol Sch Informat Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Informat Photon Technol Guangzhou 510006 Peoples R China Minist Educ Key Lab Photon Technol Integrated Sensing & Commun Guangzhou 510006 Peoples R China Huaxun Anjue Intelligent Mine Co Ltd Shenzhen Peoples R China Guangdong Univ Technol Sch Automat Guangdong Prov Key Lab Cyber Phys Syst Guangzhou 510006 Peoples R China

The image resolution and contraband object detection accuracy are the two key factors for security checks based on millimeter wave imaging techniques. In this paper, a homemade real-time millimeter imaging system for small package security inspection is used to obtain about 400 raw images of envelopes containing multi -contraband objects like guns and knives. After pre -processing, spatial transformer-feature fusion (ST-FF) adapted single -shot multi -box detector (SSD) networks are used to detect the contraband objects of postal packages. The experiments reveal that the spatial-transformed-feature fusion deep learning networks demonstrate better mean average precision (mAP) performance than traditional single networks in detecting contraband objects of different scales, orientations, and distortions, and prove the great potential for security checks based on millimeter wave imaging. (c) 2024 Optica Publishing Group

关键词： deep learning image resolution Imaging systems Imaging techniques Millimeter waves real time imaging

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Implementation of real-time Cardiologist-Level Arrhythmia Detection and Classification in Electrocardiograms Using Novel deep learning

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 2024年第0期 3662-3683页

作者： Chandrasekaran, Saravanakumar Chandran, Srinivasan Selvam, Immaculate Joy SRM Valliammai Engn Coll ECE Chennai Tamil Nadu India Rajalakshmi Engn Coll EEE Chennai Tamil Nadu India Saveetha Engn Coll ECE Chennai Tamil Nadu India

Cardiac arrhythmia refers to irregular heartbeats caused by anomalies in electrical transmission in the heart muscle, and it is an important threat to cardiovascular health. Conventional monitoring and diagnosis still depend on the laborious visual examination of electrocardiogram (ECG) devices, even though ECG signals are dynamic and complex. This paper discusses the need for an automated system to assist clinicians in efficiently recognizing arrhythmias. The existing machine-learning (ML) algorithms have extensive training cycles and require manual feature selection;to eliminate this, we present a novel deep learning (DL) architecture. Our research introduces a novel approach to ECG classification by combining the vision transformer (ViT) and the capsule network (CapsNet) into a hybrid model named ViT-Cap. We conduct necessary preprocessing operations, including noise removal and signal-to-image conversion using short-time Fourier transform (SIFT) and continuous wavelet transform (CWT) algorithms, on both normal and abnormal ECG data obtained from the MIT-BIH database. The proposed model intelligently focuses on crucial features by leveraging global and local attention to explore spectrogram and scalogram image data. Initially, the model divides the images into smaller patches and linearly embeds each patch. Features are then extracted using a transformer encoder, followed by classification using the capsule module with feature vectors from the ViT module. Comparisons with existing conventional models show that our proposed model outperforms the original ViT and CapsNet in terms of classification accuracy for both binary and multi-class ECG classification. The experimental findings demonstrate an accuracy of 99% on both scalogram and spectrogram images. Comparative analysis with state-of-the-art methodologies confirms the superiority of our framework. Additionally, we configure a field-programmable gate array (FPGA) to implement the proposed model for real-time ar

关键词： accuracy arrhythmia capsule network deep learning electrocardiogram field-programmable gate array power processing time vision transformer

来源：评论

学校读者我要写书评

暂无评论

Classification of real and bogus transients using active learning and semi-supervised learning

引用

ASTRONOMY & ASTROPHYSICS 2025年 693卷

作者： Liu, Yating Fan, Lulu Hu, Lei Lu, Junqiang Lu, Yan Xu, Zelin Zhu, Jiazheng Wang, Haochen Kong, Xu Univ Sci & Technol China Sch Artificial Intelligence & Data Sci Hefei 230026 Peoples R China Univ Sci & Technol China Dept Astron CAS Key Lab Res Galaxies & Cosmol Hefei 230026 Peoples R China Univ Sci & Technol China Sch Astron & Space Sci Hefei 230026 Peoples R China Deep Space Explorat Lab Hefei 230088 Peoples R China Carnegie Mellon Univ McWilliams Ctr Cosmol Dept Phys 5000 Forbes Ave Pittsburgh PA 15213 USA Shanghai AI Lab Shanghai 200232 Peoples R China Purple Mt Observ Nanjing 210023 Peoples R China

Context. The mounting data stream of large time-domain surveys renders the visual inspections of a huge set of transient candidates impractical. Techniques based on deep learning-based are popular solutions for minimizing human intervention in the time domain community. The classification of real and bogus transients is a fundamental component in real-time data processing systems and is critical to enabling rapid follow-up observations. Most existing methods (supervised learning) require sufficiently large training samples with corresponding labels, which involve costly human labeling and are challenging in the early stages of a time-domain survey. One method that can make use of training samples with access to only a limited amount of labels is highly desirable for future large time-domain surveys. These include the forthcoming 2.5-meter Wide-Field Survey Telescope (WFST) six-year survey and the Vera C. Rubin Observatory Legacy Survey of Space and time (LSST). Aims. deep-learning-based methods have been favored in astrophysics owing to their adaptability and remarkable performance. They have been applied to the task of the classification of real and bogus transients. Unlike most existing approaches, which necessitate massive and expensive annotated data, we aim to leverage training samples with only 1000 labels and discover real sources that vary in brightness over time in the early stages of the WFST six-year survey. Methods. We present a novel deep learning method that combines active learning and semi-supervised learning to construct a competitive real-bogus classifier. Our method incorporates an active learning stage, where we actively select the most informative or uncertain samples for annotation. This stage aims to achieve higher model performance by leveraging fewer labeled samples, thus reducing annotation costs and improving the overall learning process efficiency. Furthermore, our approach involves a semi-supervised learning stage that exploits the unlab

关键词： techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

Single-Subject deep-learning image Reconstruction With a Neural Optimization Transfer Algorithm for PET-Enabled Dual-Energy CT Imaging

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 4075-4089页

作者： Li, Siqi Zhu, Yansong Spencer, Benjamin A. Wang, Guobao Univ Calif Davis Hlth Dept Radiol Sacramento CA 95817 USA Univ Calif Davis Dept Biomed Engn Davis CA 95616 USA

Combining dual-energy computed tomography (DECT) with positron emission tomography (PET) offers many potential clinical applications but typically requires expensive hardware upgrades or increases radiation doses on PET/CT scanners due to an extra X-ray CT scan. The recent PET-enabled DECT method allows DECT imaging on PET/CT without requiring a second X-ray CT scan. It combines the already existing X-ray CT image with a 511 keV $\gamma $ -ray CT (gCT) image reconstructed from time-of-flight PET emission data. A kernelized framework has been developed for reconstructing gCT image but this method has not fully exploited the potential of prior knowledge. Use of deep neural networks may explore the power of deep learning in this application. However, common approaches require a large database for training, which is impractical for a new imaging method like PET-enabled DECT. Here, we propose a single-subject method by using neural-network representation as a deep coefficient prior to improving gCT image reconstruction without population-based pre-training. The resulting optimization problem becomes the tomographic estimation of nonlinear neural-network parameters from gCT projection data. This complicated problem can be efficiently solved by utilizing the optimization transfer strategy with quadratic surrogates. Each iteration of the proposed neural optimization transfer algorithm includes: PET activity image update;gCT image update;and least-square neural-network learning in the gCT image domain. This algorithm is guaranteed to monotonically increase the data likelihood. Results from computer simulation, real phantom data and real patient data have demonstrated that the proposed method can significantly improve gCT image quality and consequent multi-material decomposition as compared to other methods.

关键词： image reconstruction Computed tomography Positron emission tomography Optimization Kernel Imaging X-ray imaging PET-enabled dual-energy CT PET/CT image reconstruction kernel methods convolutional neural-network

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：