检索结果-内蒙古大学图书馆

2024 International Conference on computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2024

作者： Wang, Peiqi Cai, Jihao Tian, Hui Cao, Yangjie Mei, Yiduo School of Cyber Science and Engineering Zhengzhou University Henan Province Zhengzhou City450002 China Henan Province Engineering Research Center of Intelligent Sensing and Processing Henan Province Zhengzhou City450002 China Inspur Yunzhou Industrial Internet Co. Ltd. Shandong Province Jinan City250101 China

ISBN: (纸本)9781510689275

Foggy environments significantly reduce visibility, leading to degraded image quality and loss of detail in imaging devices. This affects the clarity of edge surveillance footage and the performance of real-time computer vision tasks. Although dehazing algorithms have made significant progress in various fields, most methods primarily focus on synthetic hazy images, neglecting their performance on real hazy images, resulting in issues such as color distortion and haze residue. Furthermore, existing methods often incur high computational costs, making them unsuitable for real-time dehazing in monitoring scenarios. To address these challenges, we proposed a dehazing method based on image restoration and enhancement techniques. The method integrates an RDNet designed with residual networks and attention mechanisms for image restoration, and introduces a color enhancement module to improve image quality. By using a novel composite loss function, the performance and dehazing effectiveness of RDNet are significantly improved. Experimental results show that the proposed method outperforms most models in dehazing both synthetic and real hazy images, while significantly enhancing image quality with low computational cost. This method is of great practical value for real-time dehazing in edge surveillance devices under foggy conditions. © 2025 SPIE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Precise Multi-Class Classification of Brain Tumor via Optimization Based Relevance Vector Machine

引用

intelligent Automation & Soft Computing 2023年第4期36卷 1173-1188页

作者： S.Keerthi P.Santhi Department of Computer Science Engineering Dayananda Sagar College of EngineeringBangalore560078India Department of Computer Science Engineering M.Kumarasamy College of EngineeringKarurTamil Nadu639113India

The objective of this research is to examine the use of feature selection and classiﬁcation methods for distinguishing different types of brain *** brain tumor is characterized by an anomalous proliferation of brain cells that can either be benign or *** tumors are misdiagnosed due to the variabil-ity and complexity of lesions,which reduces the survival rate in ***-sis of brain tumors via computer vision algorithms is a challenging *** and classiﬁcation of brain tumors are currently one of the most essential surgical and pharmaceutical *** brain tumor identi-ﬁcation techniques require manual segmentation or handcrafted feature extraction that is error-prone and *** the proposed research work is mainly focused on medical image processing,which takes Magnetic Resonance Imaging(MRI)images as input and performs preprocessing,segmentation,fea-ture extraction,feature selection,similarity measurement,and classiﬁcation steps for identifying brain ***,the medianﬁlter is practically applied to the input image to reduce the *** graph-cut segmentation technique is used to segment the tumor *** texture feature is extracted from the output of the segmented *** extracted feature is selected by using the Ant Colony Opti-mization(ACO)algorithm to improve the performance of the classiﬁ*** prob-abilistic approach is used to solve computing *** Euclidean distance is used to calculate the degree of similarity for each extracted *** selected feature value is given to the Relevance Vector Machine(RVM)which is a multi-class classiﬁcation ***,the tumor is classiﬁed as abnormal or *** experimental result reveals that the proposed RVM technique gives a better accuracy range of 98.87%when compared to the traditional Support Vector Machine(SVM)technique.

关键词： Brain tumor segmentation classiﬁcation relevance vector machine(RVM) ant colony optimization(ACO)

来源：评论

学校读者我要写书评

暂无评论

Deep learning serves traffic safety analysis: A forward-looking review

引用

IET intelligent TRANSPORT SYSTEMS 2023年第1期17卷 22-71页

作者： Razi, Abolfazl Chen, xiwen Li, Huayu Wang, Hao Russo, Brendan Chen, Yan Yu, Hongbin Clemson Univ Sch Comp Clemson SC 29634 USA Univ Arizona Dept Elect & Comp Engn Tucson AZ 85721 USA No Arizona Univ Dept Civil Engn Flagstaff AZ 86011 USA Arizona State Univ Polytech Sch Mesa AZ USA Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ USA

This paper explores deep learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasising driving safety for both autonomous vehicles and human-operated vehicles. A typical processing pipeline is presented, which can be used to understand and interpret traffic videos by extracting operational safety metrics and providing general hints and guidelines to improve traffic safety. This processing framework includes several steps, including video enhancement, video stabilisation, semantic and incident segmentation, object detection and classification, trajectory extraction, speed estimation, event analysis, modelling, and anomaly detection. The main goal is to guide traffic analysts to develop their own custom-built processing frameworks by selecting the best choices for each step and offering new designs for the lacking modules by providing a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step. Existing open-source tools and public datasets that can help train DL models are also reviewed. To be more specific, exemplary traffic problems are reviewed and required steps are mentioned for each problem. Besides, connections to the closely related research areas of drivers' cognition evaluation, crowd-sourcing-based monitoring systems, edge computing in roadside infrastructures, automated driving systems-equipped vehicles are investigated, and the missing gaps are highlighted. Finally, commercial implementations of traffic monitoring systems, their future outlook, and open problems and remaining challenges for widespread use of such systems are reviewed.

关键词： traffic engineering computing speed estimation traffic analysts operational safety metrics video signal processing remaining challenges learning (artificial intelligence) road safety trajectory extraction providing general hints open problems Neural nets video enhancement video stabilisation traffic videos anomaly detection Optical, image and video signal processing computer vision and image processing techniques traffic safety analysis exemplary traffic problems autonomous vehicles Traffic engineering computing object detection deep learning (artificial intelligence) required steps open-source tools crowd-sourcing-based monitoring systems custom-built processing frameworks driving safety deep learning methods traffic monitoring systems event analysis intelligent transportation systems Video signal processing road traffic successful conventional DL-based algorithms traffic video analysis edge computing road vehicles typical processing pipeline semantic incident segmentation processing framework comparative analysis automated driving systems-equipped vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel computer vision Algorithm for Enhancing Image Recognition and Classification

A Novel Computer Vision Algorithm for Enhancing Image Recogn...

引用

IEEE International Conference on Power, intelligent Computing and Systems (ICPICS)

作者： Herun Zhong School of Arts and Design Hubei University of Technology Wuhan China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

computer vision focuses on optimizing computers to understand and interpret visual data from photos or movies, while image recognition specializes in detecting and categorizing objects or patterns in photographs. Technological advancements have revolutionized the field of computer science and found applications in various fields such as robotics, healthcare, security, and entertainment. This article offers a comprehensive overview of the novel approaches of computer vision algorithms widely used in enhancing image recognition and classification. The discipline deals with extracting, analyzing, and understanding information from images or videos by developing algorithms that enable robots to see and comprehend visual information similar to humans. Image recognition primarily emphasizes automatic identification and categorization of objects or patterns in pictures. According to findings, significant developments have been made due to large datasets availability along with improvements in deep learning techniques leveraging enhanced processor power. Convolutional neural networks are now the dominant approach for image recognition problems within deep learning field attaining consistently high-performance levels across several benchmarks.

关键词： Deep learning computer vision Visualization Image recognition Benchmark testing Visual systems Classification algorithms Object recognition Convolutional neural networks Videos

来源：评论

学校读者我要写书评

暂无评论

Power vision Edge computer Device Design Based on AI Chip Atlas 200

Power Vision Edge Computer Device Design Based on AI Chip At...

引用

2023 International Conference on Electronic Materials and Information Engineering, EMIE 2023

作者： Deng, Song xu, Changbao xin, Mingyong Electric Power Research Institute of Guizhou Power Grid Co. Ltd. Guizhou Guiyang550002 China

ISBN: (纸本)9781510671331

Power vision is a technology that utilizes image processing and analysis techniques for intelligent recognition and monitoring of devices and environments in the power system. The application of power vision faces challenges such as insufficient data transmission bandwidth, poor real-time data processing, and inadequate data security and privacy protection, which limit the efficiency and quality of power vision applications. In order to address these challenges, this paper presents a design of a power vision edge computing device based on the AI chip Atlas 200, enabling real-time processing and analysis of power vision images at the edge, closer to the data source. This paper introduces the overall design of the device, software deployment, and the migration of deep learning algorithms. Furthermore, it showcases the effectiveness and advantages of the device in the specific application scenario of transmission line icing detection. © 2023 SPIE · 0277-786x ·

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Deep learning for understanding multilabel imbalanced Chest x-ray datasets

引用

FUTURE GENERATION computer SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2023年 144卷 291-306页

作者： Liz, Helena Huertas-Tato, Javier Sanchez-Montanes, Manuel Del Ser, Javier Camacho, David Univ Politecn Madrid Comp Syst Engn Dept Alan Turing S-N Madrid 28031 Spain Univ Rey Juan Carlos Dept Comp Sci Tulipan S-N Mostoles 28933 Spain Univ Autonoma Madrid Comp Sci Dept Madrid 28049 Spain TECNALIA Basque Res & Technol Alliance BRTA P Tecnol 700 Derio 48160 Bizkaia Spain Univ Basque Country UPV EHU Bilbao 48013 Spain

Over the last few years, convolutional neural networks (CNNs) have dominated the field of computer vision thanks to their ability to extract features and their outstanding performance in classification problems, for example in the automatic analysis of x-rays. Unfortunately, these neural networks are considered black-box algorithms, i.e. it is impossible to understand how the algorithm has achieved the final result. To apply these algorithms in different fields and test how the methodology works, we need to use explainable AI techniques. Most of the work in the medical field focuses on binary or multiclass classification problems. However, in many real-life situations, such as chest x-rays, radiological signs of different diseases can appear at the same time. This gives rise to what is known as "multilabel classification problems". A disadvantage of these tasks is class imbalance, i.e. different labels do not have the same number of samples. The main contribution of this paper is a Deep Learning methodology for imbalanced, multilabel chest x-ray datasets. It establishes a baseline for the currently underutilised PadChest dataset and a new explainable AI technique based on heatmaps. This technique also includes probabilities and inter-model matching. The results of our system are promising, especially considering the number of labels used. Furthermore, the heatmaps match the expected areas, i.e. they mark the areas that an expert would use to make a decision. (c) 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Convolutional neural networks Chest x-rays Explainable AI Ensemble Methodology

来源：评论

学校读者我要写书评

暂无评论

IIRM: intelligent Information Retrieval Model for Structured Documents by One-Shot Training Using computer vision

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2023年第2期48卷 1285-1301页

作者： Guha, Abhijit Samanta, Debabrata Islam, S. K. Hafizul Christ Deemed Univ Dept Comp Sci Bangalore 560029 Karnataka India First Amer India Private Ltd Bangalore 560038 Karnataka India Indian Inst Informat Technol Kalyani Dept Comp Sci & Engn Kalyani 741235 W Bengal India

Various information retrieval algorithms have matured in recent years to facilitate data extraction from structured (with a predefined template) digital document images, primarily to manage and automate different organizations' invoice and bill reimbursement processes. The algorithms are designated either rule-based or machine-learning-based. Both approaches have respective advantages and disadvantages. The rule-based algorithms struggle to generalize and need periodic adjustments, whereas machine learning-based supervised approaches need extensive data for training and substantial time and effort for manual annotation. The proposed system attempts to address both problems by providing a one-shot training approach using image processing, template matching, and optical character recognition. The model is extensible for any structured documents such as closing disclosure, bill, tax receipt, besides invoices. The model is validated against six different structured document types obtained from a reputed title insurance (TI) company. The comprehensive analysis of the experimental results confirms entity-wise extraction accuracy between 73.91 and 100% and straight through pass 81.81%, which is within business acceptable precision for a live environment. Out of total 32 tested entities, 17 outperformed all state-of-the-art techniques, where max accuracy has been 93% with only invoices or sales receipts. The system has been set operational to assist the robotic process automation of the TI mentioned above based on the experimental results.

关键词： Digital image processing Information extraction Best match region One-shot training Structured document Template matching Title insurance

来源：评论

学校读者我要写书评

暂无评论

3D semantic segmentation under adverse weather conditions 12

3D semantic segmentation under adverse weather conditions

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Liu, Tong Lin, Yunhan Wuhan University of Science and Technology College of Computer Science and Technology No. 2 Huangjiahu West Road Hongshan District Wuhan City Hubei Province Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Systems No. 947 Heping Avenue Qingshan District Wuhan City Hubei Province Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

The accurate 3D comprehension of point cloud scenes in diverse weather conditions holds paramount significance in various applications such as autonomous driving in contemporary automobiles, outdoor operations of robots, and autonomous drones. Presently, the majority of studies on semantic segmentation algorithms for 3D point clouds primarily focus on clear weather conditions. However, adverse weather conditions introduce specific types of noise that significantly deteriorate the quality of point clouds. Consequently, this poses a challenge in achieving high accuracy and efficiency in point cloud semantic segmentation for outdoor large-scale scenarios. To tackle this issue, this paper presents a novel semantic segmentation method designed for large scenes encompassing point cloud and foggy weather conditions. We further validate our approach using the Foggy Semantickitti dataset, thereby effectively enhancing the average cross-parallel ratio while maintaining computational efficiency. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep learning for deepfakes creation and detection: A survey

引用

computer vision AND IMAGE UNDERSTANDING 2022年 223卷

作者： Thanh Thi Nguyen Quoc Viet Hung Nguyen Dung Tien Nguyen Duc Thanh Nguyen Thien Huynh-The Nahavandi, Saeid Thanh Tam Nguyen Quoc-Viet Pham Nguyen, Cuong M. Deakin Univ Sch Informat Technol Geelong Vic Australia Griffith Univ Sch Informat & Commun Technol Nathan Qld Australia Kumoh Natl Inst Technol ICT Convergence Res Ctr Gyeongbuk South Korea Deakin Univ Inst Intelligent Syst Res & Innovat Geelong Vic Australia Ho Chi Minh City Univ Technol HUTECH Fac Informat Technol Ho Chi Minh City Vietnam Pusan Natl Univ Korean Southeast Ctr Ind Revolut Leader Educ 4 Busan South Korea Univ Polytech Hauts France LAMIH UMR CNRS 8201 Valenciennes France

Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One of those deep learningpowered applications recently emerged is deepfake. Deepfake algorithms can create fake images and videos that humans cannot distinguish them from authentic ones. The proposal of technologies that can automatically detect and assess the integrity of digital visual media is therefore indispensable. This paper presents a survey of algorithms used to create deepfakes and, more importantly, methods proposed to detect deepfakes in the literature to date. We present extensive discussions on challenges, research trends and directions related to deepfake technologies. By reviewing the background of deepfakes and state-of-the-art deepfake detection methods, this study provides a comprehensive overview of deepfake techniques and facilitates the development of new and more robust methods to deal with the increasingly challenging deepfakes.

关键词： Deepfakes Face manipulation Artificial intelligence Deep learning Autoencoders GAN Forensics Survey

来源：评论

学校读者我要写书评

暂无评论

3rd International Conference on Innovations in Computational Intelligence and computer vision, ICICV 2022

3rd International Conference on Innovations in Computational...

引用

3rd International Conference on Innovations in Computational Intelligence and computer vision, ICICV 2022

ISBN: (纸本)9789819926015

The proceedings contain 57 papers. The special focus in this conference is on Innovations in Computational Intelligence and computer vision. The topics include: Attention Deficit Hyperactivity Disorder Prediction Using Resting-State Networks;Neuroinformatics Deep Learning Synthesizer Based on Impulse Control Disorder Using LSTM Cells;Wasserstein GANs-Enabled Spectral Normalization on Credit Card Fraud Detection;Classification of Bipolar Disorder Using Deep Learning Models on fMRI Data;Predicting Schizophrenia from fMRI Using Deep Learning;patrolling Robot with Facial Detection;a Graph-Based Relook Beyond Metadata for Music Recommendation;an Interpretability Assisted Empirical Study of Affective Traits in Visual Content of Disinformation;multi-scale Fusion-Based Object Detection Network for Advance Driver Assistance Systems;secured Face Recognition System Based on Blockchain with Machine Learning;Vectorization of Python Programs Using Recursive LSTM Autoencoders;phenology Detection for Croplands Using Sentinel-2 and computer vision techniques;deep Learning-Based Safety Assurance of Construction Workers: Real-Time Safety Kit Detection;Automatic Detection and Classification of Melanoma Using the Combination of CNN and SVM;CyINSAT: Cyclone Dataset from Indian National Satellite for Forecasting;classification of Ocular Diseases: A vision Transformer-Based Approach;Analyzing Performance of Masked R-CNN Under the Influence of Distortions;COVID-19 Detection in Chest x-Ray Images Using Non-iterative Deterministic Learning Classifier;multimodal Classification via Visual and Lingual Feature Layer Fusion;a Review on Rural Women’s Entrepreneurship Using Machine Learning Models;classifying Paintings/Artworks Using Deep Learning techniques;handling Class Imbalance Problem Using Feature Selection techniques: A Review;an intelligent Human Pose Recommendation System Using Feature Fusion Technique;ensemble Machine Learning algorithms for Predicting Cardiovascular Disease;AI-Based Open

关键词：

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：