检索结果-内蒙古大学图书馆

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Khaoula Ben Ali Seifeddine Messaoud Mohamed Ali Hajjaji Mohamed Atri Noureddine Liouane Laboratory of Automatic Signal Image Processing National Engineering School Monastir University Monastir Tunisia Faculty of Sciences of Monastir Monastir University Monastir Tunisia Higher Institute of Applied Sciences and Technology of Sousse Sousse University Sousse Tunisia Computer Engineering Department College of Computer Science King Khalid University Abha Saudi Arabia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Recent years have seen a rapid development in machine Learning, which has profoundly influenced many areas of science and engineering. Among them, computer vision takes the leading place, where important tasks are image classifications powered by CNNs. Despite the great performance of CNNs in complicated scenarios, they remain sensitive to so-called adversarial attacks, and deliberate perturbations leading them to incorrect predictions. Besides more innocuous consequences, this has serious security implications for critical applications, in-cluding medical diagnostics, where misclassifications might result in disastrous outcomes. This research work discusses adversarial attacks on CNNs and other DNNs in computer vision, studying a full range of the generation and detection methods with details while discussing intrinsic vulnerability and robustness. It also proposes a learning framework that will enhance the robustness and security of DNNs and CNNs against such adversarial perils. The ultimate goal is directed to an improvement in the reliability of such models in absolutely critical scenarios for safe deployment into applications where accuracy is crucial.

关键词： Computer vision Accuracy Perturbation methods Computer network reliability machine learning Robustness Security Medical diagnosis Resilience image classification

来源：评论

学校读者我要写书评

暂无评论

Polarization-independent, high-NA edge detection with nonlocal metasurfaces

引用

Optics Letters 2025年第11期50卷 3517-3520页

作者： Liu, Yalong Li, Xiaoxin Shi, Bojian Jia, Qi Zhang, Yanxia Gao, Yanyu Gao, Wenya Sun, Fangkui Cao, Yongyin Feng, Rui Ding, Weiqiang Institute of Advanced Photonics School of Physics Harbin Institute of Technology Harbin 150001 China Key Laboratory of Micro-Nano Optical-acoustic-electronic System of Ministry of Industry and Information Technology Harbin 150001 China Collaborative Innovation Center of Extreme Optics Shanxi University Shanxi Taiyuan 030006 China

Optical analog computing based on flat optical structures offers significant advantages in system miniaturization, loss reduction, and computational speed compared to traditional systems requiring complex optical configurations. However, existing metasurface schemes for analog image processing suffer from critical limitations, including polarization dependence, bandwidth constraints, and restricted numerical aperture (NA). In this work, we demonstrate a robust and easy-to-fabricate nonlocal dielectric metasurface, which can readily perform polarization-independent edge detection with extended bandwidth and high NA. The isotropic two-dimensional second-order differentiation operations under arbitrary polarization conditions, including unpolarized illumination, are realized by leveraging the magnetic dipole resonance (MD). This scheme enables real-time, high-quality edge detection, featuring a bandwidth of 48 nm centered at 1064 nm and a NA of up to 0.5. This work provides a novel, to the best of our knowledge, approach for achieving polarization-independent edge detection, paving the way for practical applications in optical computing and imaging systems. © 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： Biomedical imaging Edge detection Imaging systems machine vision Optical computing Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Robust occlusion-aware orbital angular momentum feature extraction via all-optical diffractive processing systems

引用

Optics Express 2025年第11期33卷 23053-23064页

作者： Keyao Li Yuetian Jia Min Gu Xinyuan Fang School of Artificial Intelligence Science and Technology University of Shanghai for Science and Technology Shanghai 200093 China Institute of Photonic Chips University of Shanghai for Science and Technology Shanghai 200093 China yuetianjia@*** xinyuan.fang@***

As a brain-inspired optical computing architectures, diffractive optical neural networks (DONN) harness light’s wave nature for high-speed, energy efficient and parallel information processing, enabling applications such as image classification and wavefront shaping. However, conventional spatially encoded DONNs struggle with robustness in complex and unpredictable environments, where occlusions and distortions degrade processing accuracy. To address these challenges, we propose a robust all-optical feature extraction framework based on orbital angular momentum (OAM). This approach converts optical information into target OAM modes using a diffractive processing framework trained via deep learning, enabling stable and efficient information representation in the OAM domain. Unlike conventional DONNs, our method maintains high performance across diverse and irregular occlusions without requiring network retraining. This self-adaptive occlusion immune operates with zero additional training samples, effectively enhancing optical computing tasks under dynamic and uncertain conditions. By fully utilizing the helical wavefront and orthogonality of OAM, our approach improves the robustness and scalability of DONNs, demonstrating superior performance in challenging optical environments. Our work paves the way for next-generation optical computing systems that can operate reliably in unpredictable and occlusion-rich environment, unlocking what we believe to be new possibilities for robust, real-time processing in a variety of applications.

关键词： Deep learning machine vision Mode conversion Optical computing Optical neural systems Optical systems

来源：评论

学校读者我要写书评

暂无评论

i-WiViG: Interpretable Window vision GNN

arXiv

引用

arXiv 2025年

作者： Obadic, Ivica Kangin, Dmitry Oliveira, Dario Angelov, Plamen P. Zhu, Xiao Xiang Technical University of Munich Germany Munich Center for Machine Learning Germany University of Lancaster United Kingdom University of Machester United Kingdom Getulio Vargas Foundation Brazil

Deep learning models based on graph neural networks have emerged as a popular approach for solving computer vision problems. They encode the image into a graph structure and can be beneficial for efficiently capturing the long-range dependencies typically present in remote sensing imagery. However, an important drawback of these methods is their black-box nature which may hamper their wider usage in critical applications. In this work, we tackle the self-interpretability of the graph-based vision models by proposing our Interpretable Window vision GNN (i-WiViG) approach, which provides explanations by automatically identifying the relevant subgraphs for the model prediction. This is achieved with window-based image graph processing that constrains the node receptive field to a local image region and by using a self-interpretable graph bottleneck that ranks the importance of the long-range relations between the image regions. We evaluate our approach to remote sensing classification and regression tasks, showing it achieves competitive performance while providing inherent and faithful explanations through the identified relations. Further, the quantitative evaluation reveals that our model reduces the infidelity of post-hoc explanations compared to other vision GNN models, without sacrificing explanation sparsity. © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Automated Conversion of Axis-Aligned to Polygonal and Oriented Bounding Box Annotations in Aerial imagery Object Detection 25th

A Methodology for Automated Conversion of Axis-Aligned to Po...

引用

25th International Conference on Intelligent Data Engineering and Automated Learning

作者： Freire, Daniela L. de Carvalho, Andre C. P. L. F. Peterlevitz, Augusto Jose Chinelatto, Mateus Antonio da Silva, Ricardo Dutra Rojas Perea, Juan Fernando Univ Sao Paulo Inst Math & Comp Sci Sao Carlos SP Brazil Inst Pesquisas Eldorado Campinas Brazil Transmissora Alianca Energia Elet SA Belo Horizonte MG Brazil

ISBN: (纸本)9783031777370;9783031777387

Object detection in aerial imagery presents significant challenges in computer vision due to the varied orientations and complex backgrounds of objects such as buildings and vehicles. Current annotation tools often fail to accurately delineate these objects, relying on manual bounding box methods that are both time-consuming and inconsistent. Our novel methodology automates the conversion of axis-aligned annotations into polygonal and rotated annotations, prioritising systematic and scalable enhancements to data quality rather than modifying the model itself. Precise annotations, crucial for determining object locations and boundaries, are fundamental to this approach. We evaluated this methodology through a case study involving electrical transmission towers in aerial images, using advanced object detectors based on variations of the YOLOv8 algorithm. Preliminary results indicate that our automated method not only improves annotation accuracy but also significantly reduces the manual effort required, thereby lowering overall costs and time for data preparation in object detection training. The success of this methodology underscores its potential for broader applications and further advancements in automated annotation technologies.

关键词： Object Detection image Segmentation machine Learning YOLO Model Segment Anything Model Oriented Bounding Box Polygonal Annotation Annotation Conversion

来源：评论

学校读者我要写书评

暂无评论

TempA-VLP: Temporal-Aware vision-Language Pretraining for Longitudinal Exploration in Chest X-Ray image

TempA-VLP: Temporal-Aware Vision-Language Pretraining for Lo...

引用

IEEE Workshop on applications of Computer vision (WACV)

作者： Zhuoyi Yang Liyue Shen University of Michigan

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Longitudinal medical image processing is a significant task to understand the dynamic changes of disease by taking and comparing image series over time, providing insights into how conditions evolve and enabling more accurate di-agnosis and treatment planning. While recent advance-ments in biomedical vision-Language Pre-training (VLP) have enabled label-efficient representation learning with paired medical images and reports, existing methods pri-marily pair a single image with the corresponding textual report, limiting their ability to capture temporal relation-ships. To address this limitation, it is essential to learn temporal-aware cross-modal representations from sequen-tial medical images and text reports that highlight the tem-poral changes occurring between examinations. Specifi-cally, we introduce TempA- Vlp, a temporal-aware vision language pre-training framework with a cross-exam en-coder to integrate the information from both prior and cur-rent examinations. This approach enables the model to capture dynamic representations that reflect disease pro-gression over time, which allows us to (i) achieve state-of-the-art performance in disease progression classification, (ii) localize dynamic progression regions across consecutive examinations, as demonstrated in our new task, dynamic phrase grounding on the Chest-imagenome Gold dataset, and (iii) highlight progression localized regions, often rele-vant to lesion areas, which in turn improves disease classi-fication tasks on a single image.

关键词： Representation learning Accuracy Limiting Grounding Planning Lesions X-ray imaging Standards Biomedical imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

A New Video Summarization Approach Using Object Density Based image Similarity for Smart City applications

A New Video Summarization Approach Using Object Density Base...

引用

International Scientific-Professional Conference on Information Technology (IT)

作者： Turan Goktug Altundogan Mehmet Karakose Fatih Mert Computer Engineering Department Manisa Celal Bayar University Manisa Türkiye Computer Engineering Department Firat University Elazig Türkiye Huawei Telecommunication Foreign Trade Co. Ltd. Istanbul Türkiye

ISBN: (数字)9798331517649

ISBN: (纸本)9798331517656

Summarization approaches are currently proposed solutions that focus on meaningfully reducing different types of data such as text, audio, and video. Many techniques such as machine learning, signal processing, image processing, computer vision, and deep learning can be used to develop summarization approaches. In this study, we performed object detection on videos that can be used in smart city applications using a pretrained YOLOv8 model. As a result of the object detection, we created a feature vector for each image frame by using the location information covered by the classes used in the object detection process. Then, we used several different approaches to determine the reference feature vector for the video. Finally, we calculated the cosine similarities of the feature vector for each frame to this reference feature vector using different methods. With the method we developed, we presented a similarity-focused summary created by selecting the video frames expressed with maximum similarity. We also developed an evaluation approach to evaluate the summaries we presented, comparing the overall heat maps of the video with the heat maps of the summary videos. Experimental results demonstrate the efficiency of our summarization approaches.

关键词： Deep learning Computer vision Smart cities Computational modeling Object detection Signal processing Feature extraction Vectors Heat maps Information technology

来源：评论

学校读者我要写书评

暂无评论

Dimensional Accuracy Evaluation of Single-Layer Prints in Direct Ink Writing Based on machine vision

引用

Sensors 2025年第8期25卷 2543-2543页

作者： Tu, Yongqiang Zhang, Haoran Chen, Hu Bao, Baohua Fang, Canmi Wu, Hao Chen, Xinkai Hassan, Alaa Boudaoud, Hakim College of Marine Equipment and Mechanical Engineering Jimei University Xiamen361021 China Innovation Process Research Institute University of Lorraine NancyF-54000 France

The absence of standardized evaluation methodologies for single-layer dimensional accuracy significantly hinders the broader implementation of direct ink writing (DIW) technology. Addressing the critical need for precision non-contact assessment in DIW fabrication, this study develops a novel machine vision-based framework for dimensional accuracy evaluation. The methodology encompasses three key phases: (1) establishment of an optimized hardware configuration with integrated image processing algorithms;(2) comprehensive investigation of camera calibration protocols, advanced image preprocessing techniques, and high-precision contour extraction methods;and (3) development of an iterative closest point (ICP) algorithm-enhanced evaluation system. The experimental results demonstrate that our machine vision system achieves 0.04 mm × 0.04 mm spatial resolution with the ICP convergence threshold optimized to 0.001 mm. The proposed method shows an 80% improvement in measurement accuracy (0.001 mm) compared to conventional approaches. Process parameter optimization experiments validated the system’s effectiveness, showing at least 76.3% enhancement in printed layer dimensional accuracy. This non-contact evaluation solution establishes a robust framework for quantitative quality control in DIW applications, providing critical insights for process optimization and standardization efforts in additive manufacturing. © 2025 by the authors.

关键词： Statistical process control

来源：评论

学校读者我要写书评

暂无评论

Need for Speed: A Comprehensive Benchmark of JPEG Decoders in Python

arXiv

引用

arXiv 2025年

作者： Iglovikov, Vladimir Ternaus Inc.

image loading represents a critical bottleneck in modern machine learning pipelines, particularly in computer vision tasks where JPEG remains the dominant format. This study presents a systematic performance analysis of nine popular Python JPEG decoding libraries on different computing architectures. We benchmark traditional image processing libraries (Pillow, OpenCV), machine learning frameworks (TensorFlow, PyTorch), and specialized decoders (jpeg4py, kornia-rs) on both ARM64 (Apple M4 Max) and x86 64 (AMD Threadripper) platforms. Our findings reveal that modern implementations using libjpeg-turbo achieve up to 1.5x faster decoding speeds compared to traditional approaches. We provide evidence-based recommendations for choosing optimal JPEG decoders across different scenarios, from high-throughput training pipelines to real-time applications. This comprehensive analysis helps practitioners make informed decisions about image loading infrastructure, potentially reducing training times and improving system efficiency. © 2025, CC BY.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Refiner: Fine-grained Cross-modal Concepts Refinement for Compositional Zero-Shot Learning

Refiner: Fine-grained Cross-modal Concepts Refinement for Co...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xiao Zhang Haodong Jing Hui Chen Yongqiang Ma Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent Compositional Zero-Shot Learning (CZSL) methods increasingly adopt the pre-trained vision-language models to capture the contextual relations between image and text spaces. However, the single-class-token design from Transformer-based encoder inevitably captures contextual information from unrelated objects and background, thus hindering the modeling of fine-grained class-specific visual features. Suffering from cross-modal gap, prior methods also struggle to improve compositional recognition performance. To address these issues, we propose a fine-grained cross-modal concepts refinement framework, termed as Refiner, which comprises two pivotal components: (i) the fine-grained concepts refinement of image embeddings to capture state-object context within visual scenes, and (ii) the cross-modal information fusion to mitigate the modality gap. By leveraging learnable query vectors to capture region-specific semantic information pertinent to composition labels, our approach refines visual representations with fine-grained state-object context information. As for cross-modal information fusion, we construct a robust image-to-text mapping by aligning visual embeddings with states, objects, and compositions, respectively. Extensive experiments demonstrate that our Refiner achieves new state-of-the-art performance across all popular benchmarks in both closed- and open-world settings.

关键词： Visualization Zero shot learning Semantics Benchmark testing Signal processing Transformers Vectors Acoustics Speech processing Context modeling

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：