检索结果-内蒙古大学图书馆

Capacity planning of a microservices-based image classification application using analytic modeling

COMPUTING 2025年第5期107卷 1-31页

作者： Zafarzade, Zahra Ataie, Ehsan Univ Mazandaran Dept Comp Engn Babolsar Iran

With the growing demand for scalable and efficient distributed systems, microservices and serverless architectures have become key enablers for modern applications. This study focuses on designing a microservices-based image classification workflow that integrates an ensemble learning algorithm to achieve robust and accurate predictions. The workflow is modeled using Extended Queueing Networks, enabling detailed representation of function stations and their associated queues. To assess system performance and ensure quality of Service, key metrics are defined, and the model is analyzed using Java Modeling Tools. performance analysis at both the station and system levels highlight critical bottlenecks and inform a capacity planning strategy to ensure stability under varying workloads. The results show that the proposed capacity planning approach can avoid overutilization by dynamically increasing the number of function instances, thus maintaining the utilization of all resources within a predefined range. This research provides valuable insights into designing reliable, scalable, and efficient workflows on Function-as-a-Service platforms, addressing the challenges of queue management and system overutilization in serverless environments.

关键词： performance modeling Extended queueing network Serverless computing Microservices quality of service image classification 65

来源：评论

学校读者我要写书评

暂无评论

A special image encryption strategy based on a novel digital chaotic system and binary block compressed sensing for fixed-point DSP

引用

NONLINEAR DYNAMICS 2025年第9期113卷 10535-10558页

作者： Dou, Yuqiang Yue, Shuang Zhang, xinke Fan, Haiju Li, Ming Zhang, Mingzhu Henan normal Univ Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang 453007 Henan Peoples R China

The paper introduced an image encryption strategy that uses a novel digital chaotic system and block compressed sensing (BCS). It is better suited for fixed-point digital signal processors (DSP). Firstly, the digital logistic chaotic system and the digital Chebyshev chaotic systems are combined to create a novel digital chaotic system. After that, a binary measurement matrix is created using the suggested novel digital chaotic system. Next, the obtained images are processed in blocks and the image is compressed sensing by the measurement matrix. Finally, re-encrypting the cipher images by diffusion processing over a finite domain. The Projected Landwebe algorithm and wiener filter are used to speed up the decryption process and improve the quality of image decryption. Simulation tests and performance analysis demonstrate the strong unpredictability of the proposed digital chaotic system, when the computer word length is 32, the Lyapunov exponent is about 20. It can be used to generate an image encryption scheme that is resistant to noise and exhaustion attacks and yields superior image recovery quality. When the sampling rate is 0.25, the average PSNR value and MSSIM value of the recovered image are 28.1180 dB and 0.87904, and the average information entropy of the encrypted image is 7.9991.

关键词： image encryption The novel digital chaotic system Binary measurement matrix Block compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Characterization of a prototype rapid kilovoltage x-ray image guidance system designed for a linear accelerator radiation therapy unit

引用

JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS 2025年第5期26卷 e70060页

作者： Arsenault, Theodore Arrue, Jonathan Gregg, Kenneth Baydoun, Atallah Rezai, Atefeh Langmack, Christian Henke, Lauren Spratt, Daniel E. Kashani, Rojano Price, Alex Univ Hosp Seidman Canc Ctr Dept Radiat Oncol Cleveland OH USA Case Western Reserve Univ Dept Biomed Engn Cleveland OH USA

PurposeThis study evaluates a novel cone-beam computed tomography (CBCT) imaging solution integrated onto a conventional C-arm linear accelerator (linac) with increased gantry speed. The purpose is to assess the impact of improved imaging hardware and reconstruction algorithms on image ***-CBCT (HS-CBCT) system was compared with the original system (OG-CBCT) on a TrueBeam linac. performance tests included mechanical, geometric, setup accuracy, and image quality assessment. image quality metrics were evaluated using conventional CBCT reconstruction and advanced iterative reconstruction (iCBCT), fast iCBCT, and iCBCT with metal artifact reduction. Dosimetry measurements were *** HS-CBCT system acquired images in 24.0-44.0s (half trajectory/full trajectory), faster than the OG-CBCT system's acquisition time of 33.5-60.5s (half trajectory/full trajectory). The HS-CBCT system's faster gantry speed resulted in comparable image quality to the OG-CBCT. It improved high-contrast resolution, modulation transfer function, and low-contrast visibility. The faster gantry speed also produced lower radiation doses. The system's uniformity and resolution also improved, particularly with full-fan acquisition *** novel HS-CBCT system on a conventional C-arm linac exhibits superior imaging capabilities compared to the OG-CBCT. Faster gantry speed, larger imaging area, and advanced reconstruction algorithms contribute to enhanced image quality and reduced dose. The study provides comprehensive insights into the new system's performance, serving as a benchmark for future linac installations and highlighting potential benefits in clinical applications. Further investigations are suggested for 4D acquisitions and long-term machine performance.

关键词： fast Cone-Beam CT KV-IGRT quality assurance

来源：评论

学校读者我要写书评

暂无评论

Fλ/d as a predictor of image classification algorithm performance

引用

APPLIED OPTICS 2025年第4期64卷 845-854页

作者： Hixson, Jonathan g. Teaney, Brian Finch, Michael f. Nehmetallah, George Driggers, Ronald US Army Combat Capabil Dev Command DEVCOM C5ISR Ctr RTI Aberdeen Proving Ground NY 21005 USA Catholic Univ Amer EECS Dept 620 Michigan Ave NE Washington DC 20064 USA Univ Arizona Wyant Coll Opt Sci Infrared Syst Grp Tucson AZ 85721 USA

This research studied the effect of variations in a sensor's F lambda/d metric value (FLD) on the performance of machine learning algorithms such as the YOLO (You Only Look Once) algorithm for object classification. The YOLO_v3 and YOLO_v10 algorithms were trained using static imagery provided in the commonly available training dataset provided by Teledyne FLIR systems. image processing techniques were used to degrade image quality of the test dataset also provided by Teledyne FLIR systems, simulating detector-limited to optics-limited performance, which results in a variation of the FLD metric between 0.339 and 7.98. The degraded test set was used to evaluate the performance of YOLO_v3 and YOLO_v10 for object classification and relate the FLD metric to the probability of detection. Results of YOLO_v3 and YOLO_v10 are presented for the varying levels of image degradation. A summary of the results is discussed along with recommendations for evaluating an algorithm's performance using a sensor's FLD metric value. (c) 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： image quality image sensors Imaging systems Imaging techniques Machine learning Sensor performance

来源：评论

学校读者我要写书评

暂无评论

An end-to-end intelligent welding defect detection system for low-quality x-ray images with adaptive progressive learning

引用

ExPERT systemS WITH APPLICATIONS 2025年 279卷

作者： Zuo, Fengyuan Liu, Jinhai Fu, Mingrui Wen, Zhitao Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Paidelin Technol Co Ltd Shenyang 110081 Peoples R China

Intelligent weld defect detection based on x-ray images is a paramount research topic in the field of industrial automation. Many excellent object detectors have been developed into industrial vision frameworks. Despite significant efforts, these methods still fail to effectively detect weld defects in low-quality x-ray images (low-brightness, foggy). We have carefully considered the evaluation process of human experts, and experienced engineers usually carefully adjust the details of the image, and then focus all their attention on defect evaluation after briefly browsing the image. Inspired by the above process, we develop a novel framework to detect different types of defects from low-quality x-ray images. Firstly, an adaptive image preprocessing method is designed to simulate the fine adjustment of image details (brightness, contrast) during manual evaluation. The parameters of image processing can be obtained through joint training of a differentiable preprocessing module and a back-end detector, thereby flexibly adjusting the details of the image. Secondly, a progressive feature extractor is proposed, which includes three inherently connected components: multi-view feature extraction, large-kernel perceptron, and feature recombination to simulate the rough to centralized process of manual evaluation, thereby improving the model's ability to capture defects and overall performance. In practical application, we used the weld defect dataset based on x-ray in North China. We achieved a 8.5% AP improvement (23.4 M model training parameters), with inference time of 15.9 ms per image and resolution (640 x 640).

关键词： Weld defect detection Low-quality x-ray images Expert evaluation Adaptive preprocessing Progressive feature extractor

来源：评论

学校读者我要写书评

暂无评论

Enhancing colour image contrast via analytic functions subordinate to generalized Mersenne polynomials

引用

IMAGING SCIENCE JOURNAL 2025年

作者： Aarthy, B. Keerthi, B. Srutha Vellore Inst Technol Sch Adv Sci Dept Math Chennai 600127 India

Digitally captured and transferred colour images often suffer from low contrast, impacting both human perception and automated system performance. To address this issue with minimal information loss, we propose a new contrast enhancement method using a transformation function derived from Sakaguchi type functions subordinate to Generalized Mersenne polynomials on the open unit disk. This pixel-wise transformation enhances image intensity and contrast effectively. The method is particularly well-suited for colour images, producing high-quality outputs while preserving image details. Its simplicity allows application across various image types with varying contrast degradation. We evaluate our approach on 275 low-contrast images from two datasets - Categorical image quality (CSIQ) Database and Tampere image Database (TID2013) - across five distortion levels. Also, a comparative study with other state-of-the-art techniques demonstrates that the proposed method achieves superior visual quality.

关键词： Analytic function generalized Mersenne polynomials coefficient bounds contrast enhancement transformation function

来源：评论

学校读者我要写书评

暂无评论

Efficient and robust techniques for infrared imaging system correction

引用

IMAGING SCIENCE JOURNAL 2025年第3期73卷 381-400页

作者： Hamadouche, Sid Ahmed Boutemedjet, Ayoub Bouaraba, Azzedine Ecole Mil Polytech Lab Syst Lasers BP 17 Bordj El Bahri Algiers 16111 Algeria Ecole Mil Polytech Lab Radar Algiers Algeria

Stripe noise is a prevalent issue in infrared imaging systems, characterized by its distinctive directional features, which often appear as vertical lines across the image. This type of noise can significantly degrade the quality of the captured images, making it crucial to address and mitigate its effects. This paper presents an effective strategy to tackle this problem by transforming it from a 2D image issue into a 1D signal problem, enabling efficient resolution of stripes in infrared images. By understanding the characteristics of stripe noise, the proposed algorithm effectively solves the problem by first computing the column average of the noisy image, extracting stripe components from this one-dimensional signal, and effectively removing the stripes without blurring image details. This approach has been tested on numerous images with varying noise levels, demonstrating exceptional denoising performance compared to state-of-the-art methods. The results show marked improvements in visual quality, especially around edges and smooth areas, without requiring complex algorithms or iterative processes.

关键词： Stripe noise image denoising infrared imaging systems non-uniformity correction fixed pattern noise image processing remote sensing

来源：评论

学校读者我要写书评

暂无评论

A fully automated, expert-perceptive image quality assessment system for whole-body [18F]FDG PET/CT

引用

EJNMMI RESEARCH 2025年第1期15卷 1-13页

作者： Zhang, Cong Gao, xin Zheng, xuebin xie, Jun Feng, Gang Bao, Yunchao Gu, Pengchen He, Chuan Wang, Ruimin Tian, Jiahe Med Sch Chinese PLA Beijing Peoples R China First Med Ctr Chinese PLA Gen Hosp Dept Nucl Med Beijing Peoples R China Shanghai Universal Med Imaging Diagnost Ctr Shanghai Peoples R China Shanghai Aitrox Technol Corp Ltd Dept Sci Res Shanghai Peoples R China

BackgroundThe quality of clinical PET/CT images is critical for both accurate diagnosis and image-based research. However, current image quality assessment (IQA) methods predominantly rely on handcrafted features and region-specific analyses, thereby limiting automation in whole-body and multicenter evaluations. This study aims to develop an expert-perceptive deep learning-based IQA system for [18F]FDG PET/CT to tackle the lack of automated, interpretable assessments of clinical whole-body PET/CT image *** retrospective multicenter study included clinical whole-body [18F]FDG PET/CT scans from 718 patients. Automated identification and localization algorithms were applied to select predefined pairs of PET and CT slices from whole-body images. Fifteen experienced experts, trained to conduct blinded slice-level subjective assessments, provided average visual scores as reference standards. Using the MANIQA framework, the developed IQA model integrates the Vision Transformer, Transposed Attention, and Scale Swin Transformer Blocks to categorize PET and CT images into five quality classes. The model's correlation, consistency, and accuracy with expert evaluations on both PET and CT test sets were statistically analysed to assess the system's IQA performance. Additionally, the model's ability to distinguish high-quality images was evaluated using receiver operating characteristic (ROC) *** IQA model demonstrated high accuracy in predicting image quality categories and showed strong concordance with expert evaluations of PET/CT image quality. In predicting slice-level image quality across all body regions, the model achieved an average accuracy of 0.832 for PET and 0.902 for CT. The model's scores showed substantial agreement with expert assessments, achieving average Spearman coefficients (rho) of 0.891 for PET and 0.624 for CT, while the average Intraclass Correlation Coefficient (ICC) reached 0.953 for PET and 0.92 for CT. The PET IQA model

关键词： [18F]FDG image quality assessment Positron emission tomography/Computed tomography Whole-body Deep learning

来源：评论

学校读者我要写书评

暂无评论

Scanning imaging through the scattering medium based on the guided filter assisted by a WTMM and NLM

引用

APPLIED OPTICS 2025年第10期64卷 2408-2418页

作者： Zhang, Yiyang Ding, Zhewen Li, Runze Meng, xianglei Shi, Yan Zhan, Chunlian Zhao, Chunliu China Jiliang Univ Coll Opt & Elect Technol Hangzhou 310018 Zhejiang Peoples R China State Adm Market Regulat Key Lab Light Sensing & Image Metrol Hangzhou 310018 Zhejiang Peoples R China Zhejiang Prov Key Lab Optoelect Metrol & Precis In Hangzhou 310018 Zhejiang Peoples R China

In a scanning imaging system through a scattering medium, the quality of the imaging result is related to the energy distribution of the focusing point. In actual imaging, the energy of the focusing point cannot be perfectly concentrated. The scattering noise is always surrounded by the focusing point, which reduces the signal-to-noise ratio and results in poor image quality. To improve the quality of imaging, further processing of the imaging results is required, while most conventional image processing methods can only achieve one of the goals such as noise reduction, image smoothing, edge sharpening, or maintaining image integrity. In this paper, a scanning imaging system through the scattering medium based on an adaptive guided filter assisted by the wavelet transform modulus maximum (WTMM) and non-local mean (NLM) is proposed for the first time, to the best of our knowledge, which can make the imaging results simultaneously have the advantages of low noise, high contrast, and clear details. To verify the validity of the proposed method, a scanning imaging system through the scattering medium was setup. Transmissive imaging was performed at different positions from the focal plane. The experimental results show that the background noise is significantly restrained, single-pixel response and edge continuity are good, and details are clear with the proposed method. Compared with the traditional methods and the deep learning methods, the proposed method can improve the PSNR and SSIM by up to 10.68 dB, 0.75 and 5.34 dB, 0.72, respectively. Finally, the performance of the proposed method in high-noise environments, its application in the field of real-time imaging, and future improvements are discussed. The method proposed in this paper can effectively improve the quality of scanning imaging results through the scattering medium, which is expected to promote the application of this technology in endoscopic imaging and other fields. (c) 2025 Optica Publishing Group. A

关键词： Deep learning Imaging systems Imaging techniques Real time imaging Scattering media Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Metrological performance quantification of a 3D-DIC system

引用

MEASUREMENT 2025年 249卷

作者： Yang, Haotian Zhu, Kaiyu Zhao, Jianhui Lan, Tianbao Pan, Bing Beihang Univ Sch Aeronaut Sci & Engn Natl Key Lab Strength & Struct Integr Beijing 100191 Peoples R China China Nucl Power Engn Co Ltd Beijing 100840 Peoples R China

Three-dimensional digital image correlation (3D-DIC) is widely used as a standard optical technique for shape and deformation measurement. In practice, the metrological performance of a 3D-DIC system must be fully understood and quantified to determine its measurement ranges and its measurement quality. In this work, by directly using the calibration and matching results of 3D-DIC calculation, easy-to-implement quantitative methods are proposed to evaluate key metrological parameters (i.e., common field of view (CFOV), magnification and displacement measurement uncertainty) for a 3D-DIC system. For validation, the CFOV of various 3DDIC systems with different configurations was measured. Also, translation experiments were carried out and measured by these 3D-DIC systems. The experimental results demonstrated good agreement with theoretical predictions, validating the efficacy of the proposed methods. Finally, the proposed method was employed for characterizing the deflection of a cantilever beam measured by a specific 3D-DIC system. The methods presented in this work can be easily integrated into existing 3D-DIC software for better use of this powerful technique.

关键词： Three-dimensional digital image correlation Uncertainty quantification Measurement system Metrological performance

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：