检索结果-内蒙古大学图书馆

17th International Conference on machine vision, ICMV 2024

作者： Kim, Huijun Lee, Deokwoo Keimyung University Dalgubeol-daero Dalseo-gu Daegu1095 Korea Republic of

ISBN: (纸本)9781510688278

Depth information is useful in many image processing and computer vision applications, but in photography, depth information is lost in the process of projecting a real-world scene onto a 2D plane. Extracting depth information from such images is a challenging task. In this paper, we propose a method to train a deep neural network to classify an image patch (16x16 in size) into 15 levels based on the level of blur. Blur is related to the distance between the focal plane and the object. The input image is shifted using a sliding window technique at 8 pixel intervals and the trained blur classifier evaluates each blur level. The obtained blur maps are subjected to a refinement process to quantitatively assess their accuracy and impact on the final result, and the final blur maps are compared with the labels of the actual input data to estimate the depth map. The proposed method demonstrates that depth information can be successfully extracted from a single image by classifying the focus levels. © 2025 SPIE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Training Auxiliary Prototypical Classifiers for Explainable Anomaly Detection in Medical image Segmentation 23

Training Auxiliary Prototypical Classifiers for Explainable ...

引用

23rd IEEE/CVF Winter Conference on applications of Computer vision (WACV)

作者： Cho, Wonwoo Park, Jeonghoon Choo, Jaegul IKAIST Daejeon South Korea Letsur Inc Seoul South Korea

ISBN: (纸本)9781665493468

machine learning-based algorithms using fully convolutional networks (FCNs) have been a promising option for medical image segmentation. However, such deep networks silently fail if input samples are drawn far from the training data distribution, thus causing critical problems in automatic data processing pipelines. To overcome such outof-distribution (OoD) problems, we propose a novel OoD score formulation and its regularization strategy by applying an auxiliary add-on classifier to an intermediate layer of an FCN, where the auxiliary module is helfpul for analyzing the encoder output features by taking their class information into account. Our regularization strategy train the module along with the FCN via the principle of outlier exposure so that our model can be trained to distinguish OoD samples from normal ones without modifying the original network architecture. Our extensive experiment results demonstrate that the proposed approach can successfully conduct effective OoD detection without loss of segmentation performance. In addition, our module can provide reasonable explanation maps along with OoD scores, which can enable users to analyze the reliability of predictions.

关键词： Training image segmentation machine learning algorithms Pipelines Training data Network architecture Data processing

来源：评论

学校读者我要写书评

暂无评论

Active Transfer Learning for Efficient Video-Specific Human Pose Estimation

Active Transfer Learning for Efficient Video-Specific Human ...

引用

IEEE/CVF Winter Conference on applications of Computer vision (WACV)

作者： Taketsugu, Hiromu Ukita, Norimichi Toyota Technol Inst Nagoya Aichi Japan

ISBN: (纸本)9798350318920;9798350318937

Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To address this issue, we present our approach combining Active Learning (AL) and Transfer Learning (TL) to adapt HP estimators to individual video domains efficiently. For efficient learning, our approach quantifies (i) the estimation uncertainty based on the temporal changes in the estimated heatmaps and (ii) the unnaturalness in the estimated full-body HPs. These quantified criteria are then effectively combined with the state-of-the-art representativeness criterion to select uncertain and diverse samples for efficient HP estimator learning. Furthermore, we reconsider the existing Active Transfer Learning (ATL) method to introduce novel ideas related to the retraining methods and Stopping Criteria (SC). Experimental results demonstrate that our method enhances learning efficiency and outperforms comparative methods. Our code is publicly available at: https://***/ImIntheMiddle/VATL4Pose-WACV2024

关键词： Algorithms Algorithms Algorithms and algorithms formulations image recognition and understanding machine learning architectures Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

A 619-pixel machine vision enhancement chip based on two-dimensional semiconductors

引用

SCIENCE ADVANCES 2022年第31期8卷 000-000页

作者： Ma, Shunli Wu, Tianxiang Chen, Xinyu Wang, Yin Ma, Jingyi Chen, Honglei Riaud, Antoine Wan, Jing Xu, Zihan Chen, Lin Ren, Junyan Zhang, David Wei Zhou, Peng Chai, Yang Bao, Wenzhong Fudan Univ Sch Microelect State Key Lab ASIC & Syst Shanghai 200433 Peoples R China Fudan Univ Sch Informat Sci & Technol State Key Lab ASIC & Syst Shanghai 200433 Peoples R China Shenzhen Sixcarbon Technol 188 Jiangshi Rd Shenzhen 518106 Peoples R China Hong Kong Polytech Univ Dept Appl Phys Kowloon Hung Hom Hong Kong Peoples R China

The rapid development of machine vision applications demands hardware that can sense and process visual information in a single monolithic unit to avoid redundant data transfer. Here, we design and demonstrate a monolithic vision enhancement chip with light-sensing, memory, digital-to-analog conversion, and processing functions by implementing a 619-pixel with 8582 transistors and physical dimensions of 10 mm by 10 mm based on a wafer-scale two-dimensional (2D) monolayer molybdenum disulfide (MoS2). The light- sensing function with analog MoS2 transistor circuits offers low noise and high photosensitivity. Furthermore, we adopt a MoS2 analog processing circuit to dynamically adjust the photocurrent of individual imaging sensor, which yields a high dynamic light- sensing range greater than 90 decibels. The vision chip allows the applications for contrast enhancement and noise reduction of image processing. This large-scale monolithic chip based on 2D semiconductors shows multiple functions with light sensing, memory, and processing for artificial machine vision applications, exhibiting the potentials of 2D semiconductors for future electronics.

关键词： Molybdenum disulfide

来源：评论

学校读者我要写书评

暂无评论

Attention Modules Improve image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study

Attention Modules Improve Image-Level Anomaly Detection for ...

引用

IEEE/CVF Winter Conference on applications of Computer vision (WACV)

作者： Vieira E Silva, Andre Luiz Simties, Francisco Kowerko, Danny Schlosser, Tobias Battisti, Felipe Teichrieb, Veronica Univ Fed Pernambuco Ctr Informat Voxar Labs Recife PE Brazil Tech Univ Chemnitz Jr Professorship Media Comp Chemnitz Germany Univ Fed Rural Pernambuco Visual Comp Lab DC Recife PE Brazil

ISBN: (纸本)9798350318920;9798350318937

Within (semi-)automated visual industrial inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The emergence of these often rarely occurring defect patterns explains the general need for labeled data corpora. To alleviate this issue and advance the current state of the art in unsupervised visual inspection, this work proposes a DifferNet-based solution enhanced with attention modules: AttentDifferNet. It improves image-level detection and classification capabilities on three visual anomaly detection datasets for industrial inspection: InsPLAD-fault, MVTec AD, and Semiconductor Wafer. In comparison to the state of the art, AttentDifferNet achieves improved results, which are, in turn, highlighted throughout our quali-quantitative study. Our quantitative evaluation shows an average improvement compared to DifferNet - of 1.77 +/- 0.25 percentage points in overall AUROC considering all three datasets, reaching SOTA results in InsPLAD-fault, an industrial inspection in-the-wild dataset. As our variants to AttentDifferNet show great prospects in the context of currently investigated approaches, a baseline is formulated, emphasizing the importance of attention for industrial anomaly detection both in the wild and in controlled environments.

关键词： Algorithms Algorithms and algorithms applications formulations image recognition and understanding machine learning architectures Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

machine learning and image analysis in vascular surgery

引用

SEMINARS IN VASCULAR SURGERY 2023年第3期36卷 413-418页

作者： Tomihama, Roger T. Dass, Saharsh Chen, Sally Kiang, Sharon C. Linda Univ Sch Med Dept Radiol Sect Vasc & Intervent Radiol 11234 Anderson StSuite MC-2605E Loma Linda CA 92354 USA Linda Univ Sch Med Dept Surg Div Vasc Surg Loma Linda CA USA Vet Affairs Loma Linda Healthcare Syst Dept Surg Div Vasc Surg Loma Linda CA USA

Deep leaming, a subset of machine learning within artificial intelligence, has been successful in medical image analysis in vascular surgery. Unlike traditional computer-based segmentation methods that manually extract features from input images, deep leaming methods learn image features and classify data without making prior assumptions. Convolutional neural networks, the main type of deep learning for computer vision processing, are neural networks with multilevel architecture and weighted connections between nodes that can "auto-leam" through repeated exposure to training data without manual input or supervision. These networks have numerous applications in vascular surgery imaging analysis, particularly in disease classification, object identification, semantic segmentation, and instance segmentation. The purpose of this review article was to review the relevant concepts of machine leaming image analysis and its application to the field of vascular surgery. (c) 2023 Elsevier Inc. All rights reserved.

关键词： Artificial intelligence Vascular surgery image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hardware Implementation of machine vision System for Component Detection 7th

Hardware Implementation of Machine Vision System for Compone...

引用

7th International Conference on Emerging Research in Computing, Information, Communication and applications, ERCICA 2022

作者： Smruthi, P. Prajna, K.B. John, Jibin G. Pasha, Aslam Taj VLSI and Embedded Systems Nitte Meenakshi Institute of Technology Bengaluru India Department of Electronics and Communication Nitte Meenakshi Institute of Technology Bengaluru India Research and Technology Development Group ACE Designers Ltd Bengaluru India

ISBN: (纸本)9789811954818

Inspection of components using machine vision technologies provides solution for quality and process control. This technique is used in various applications such as automotive, pharmaceutical, food and beverage, electronics, packages, process control and special application. The basic idea is to use machine vision technology in the industries to improve the production quality, reduce the scrap product due to non-conformity by controlling the manufacturing process through machine vision and also to prevent the value addition for scrap product in the subsequent stage of manufacturing process. Thus, designing and developing a machine vision system for component identification used the image processing algorithm. Inside the component, small circles which are of 0.5 diameter are detected using Hough circle detection. Graphical user interface was developed for visual representation of the image processing. The training model of the system is developed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Unveiling the vision: A Comprehensive Review of Computer vision in AI and ML

Unveiling the Vision: A Comprehensive Review of Computer Vis...

引用

2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems, ADICS 2024

作者： Laad, Meena Maurya, Ratan Saiyed, Najeeb Symbiosis Institute Of Technology Dept. Of Applied Science Maharashtra Pune India Symbiosis Institute Of Technology Dept. Of Artificial Intelligence And Machine Learning Maharashtra Pune India

ISBN: (纸本)9798350364828

In the era of rapid technological advancement, Computer vision has emerged as a transformative force, reshaping the landscape of Artificial Intelligence (AI) and machine Learning (ML). This comprehensive review paper aims to delve into the intricate evolution, methodologies, applications, challenges, and future trajectories of Computer vision. Moving beyond a mere exploration of technical intricacies, our objective is to present a holistic narrative that encapsulates the profound impact of computer vision on AI and ML and its repercussions across society. The journey begins by traversing the philosophical and historical roots of Computer vision, unraveling the threads that connect human visual perception to the development of artificial vision. By exploring the historical evolution from early image processing to the current era of deep learning, we seek to elucidate the intellectual milestones that have shaped the field. Methodologically, this paper navigates through both traditional approaches and contemporary deep learning paradigms. It dissects traditional methods, emphasizing their enduring relevance and influence on modern Computer vision applications. In parallel, exploring deep learning delves into established architectures all the nuanced impact of design choices on interpretability and explain ability. applications form a cornerstone of our review, with an enriched focus on case studies that spotlight the transformative influence of Computer vision. Beyond the traditional domains of image recognition, we delve into the healthcare renaissance, where Computer vision contributes to diagnostics, drug discovery, and personalized medicine. Furthermore, we explore its role in smart cities, extending beyond surveillance to urban planning, traffic management, and environmental monitoring. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Generative Artificial Intelligence for Hyperspectral Sensor Data: A Review

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6422-6439页

作者： Abuhani, Diaa Addeen Zualkernan, Imran Aldamani, Raghad Alshafai, Mohamed Amer Univ Sharjah Dept Comp Sci & Engn Sharjah 26666 U Arab Emirates

Airborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative artificial intelligence (GAI) in the advancement of HSI processing. GAI methods address the inherent challenges of HSI data, such as high dimensionality, noise, and the need to preserve spectral-spatial correlations, rendering them indispensable for modern HSI analysis. Generative neural networks, including generative adversarial networks and denoising diffusion probabilistic models, are highlighted for their superior performance in classification, segmentation, and object identification tasks, often surpassing traditional approaches, such as U-Nets, autoencoders, and deep convolutional neural networks. Diffusion models showed competitive performance in tasks, such as feature extraction and image resolution enhancement, particularly in terms of inference time and computational cost. Transformer architectures combined with attention mechanisms further improved the accuracy of generative methods, particularly for preserving spectral and spatial information in tasks, such as image translation, data augmentation, and data synthesis. Despite these advancements, challenges remain, particularly in developing computationally efficient models for super-resolution and data synthesis. In addition, novel evaluation metrics tailored to the complex nature of HSI data are needed. This review underscores the potential of GAI in addressing these challenges while presenting its current strengths, limitations, and future research directions.

关键词： Feature extraction Hyperspectral imaging image segmentation Satellites Spatial resolution machine learning Neural networks Reviews Noise measurement Data models Diffusion models generative adversarial networks (GANs) generative artificial intelligence (GAI) generative neural networks (GNNs) hyperspectral images

来源：评论

学校读者我要写书评

暂无评论

Scenario-Based Synthetic Data Generation for an AI-based System Using a Flight Simulator

Scenario-Based Synthetic Data Generation for an AI-based Sys...

引用

AIAA SciTech Forum

作者： Sprockhoff, Jasper Gupta, Siddhartha Durak, Umut Krueger, Thomas German Aerosp Ctr DLR Inst Flight Syst Braunschweig Germany German Aerosp Ctr DLR Inst AI Safety & Security St Augustin Germany

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

In recent years, algorithms based on machine learning have significantly advanced many technical areas, including computer vision. Since the performance of machine learning applications is data-dependent, a sufficient amount of high-quality data must be available to achieve robust and stable performance. However, the collection of large amounts of real-world data that covers the operational parameters of the AI-based system is often a difficult task because of availability, cost, or even potential danger. Therefore, synthetic data generation is often used to supplement data sets with additional required data samples. In this paper, we propose a baseline for an automated toolchain to generate synthetic image data of aircraft for machine-learning computer vision applications using a flight simulator. Scenario-based approaches have shown applicability to systematically generate valid test cases for system safety evaluation. We leverage a similar approach to generate data for training of AI-based systems. Our approach requires the user to create scenario models using our modelling tool. These models define the operational ranges for a set of parameters that characterize executable scenarios. The scenarios defined by the models are used to automatically produce images from simulations carried out with the FlightGear open-source flight simulator. We distinguish between a static and a dynamic simulation approach. The static approach generates a sequence of independent scenes, while the dynamic approach creates situations that mimic a collision avoidance scenario. With our approach, we can automatically generate large amounts of raw image data covering the relevant parameter ranges based on the models created by the user.

关键词： Flight Simulators machine Learning Computer vision Collision Avoidance System System Entity Structure Aviation Flight Planning Python Generative Adversarial Network Natural Language processing

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：