检索结果-内蒙古大学图书馆

29th International Conference on Information Technology, IT 2025

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

ISBN: (纸本)9798331517649

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. © 2025 IEEE.

关键词： image Similarity Object Detection Smart City video Summarization

来源：评论

学校读者我要写书评

暂无评论

A machine Learning based Facial Expression and Emotion Recognition for Human Computer Interaction through Fuzzy Logic System 6

A Machine Learning based Facial Expression and Emotion Recog...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： vinutha, K. Niranjan, Manoj Kumar Makhijani, Jagdish Natarajan, B. Nirmala, v. vijaya Lakshmi, T.R. Department of Information Science and Engineering BMS Institute of Technology and Management Karnataka Bengaluru India Department of Computer Applications Rustamji Institute of Technology Madhya Pradesh Gwalior India Department of Computer Science and Engineering Rustamji Institute of Technology Madhya Pradesh Gwalior India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Tamil Nadu Chennai India Department of Science and Humanities Faculty of Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Mahatma Gandhi Institute of Technology Telangana Hyderabad India

ISBN: (纸本)9798350398496

Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase where many service providers use this feature to find the expression of the people on using their BlogSpot or website or reading any news article. This recognition of facial expression is highly possible with the help of machine learning technology. This research study has developed a facial expression recognizing algorithm using Python programming language with the help of Keras software package. This algorithm is purely based on machine learning approach that enables the programmer to process the facial image and convert it into data that is helpful in prediction of facial expression using the fuzzy logic technique. The fuzzy logic technique is a prediction method that helps programmer to predict the intermediate data by providing the initial and ending conditions. For enabling the facial recognition to process any system or a mobile device the algorithm needs permission to access the camera, once the onto the access is permitted the algorithm retrieves the image from the vision sensor and with the help of image processing technology of the machine learning algorithm the program the program converts the data from the vision sensor into required facial expression and emotional content. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Efficient ODR for Computer Night vision Using Multi-Scale Retinex Network-Aided Enhanced images 4

An Efficient ODR for Computer Night Vision Using Multi-Scale...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Charles Prabu, v. Pandiaraja, P. Sathiyamoorthi, v. Durgadevi, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Government Polytechnic College Department of Computer Engineering Baisuhalli Tamilnadu Dharmapuri India Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus Tamilnadu Chennai India

ISBN: (纸本)9798331508845

In the current scenario, recognizing various objects and tracking their movements in the real-time surveillance footage is the most difficult task. To detect objects, a combination of image processing and computer vision algorithms is utilized. Computer-vision based automatic human activity recognition from surveillance video can be utilized for applications such as the identification of violent acts and the study of human behavior. Consequently, this work implements a new "Object Detection and Recognition (ODR)"model for computer night vision utilizing a deep learning technique. In order to improve the supplied input image, the combined images are first transmitted to the "Multi-scale Retinex (MSR)"model. The You Only Look Once version 7 (Yolov7) model uses the improved image from MSR as input to identify and recognize things. After conducting experiments, the implemented ODR model on the ExDark Dataset obtained an efficiency of 94.8%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A machine learning model for Alzheimer's disease prediction

引用

IET CYBER-PHYSICAL SYSTEMS: THEORY & applications 2024年第2期9卷 125-134页

作者： Rani, Pooja Lamba, Rohit Sachdeva, Ravi Kumar Kumar, Karan Iwendi, Celestine Maharishi Markandeshwar Deemed Univ MMICTBM Ambala Haryana India Maharishi Markandeshwar Deemed Univ Maharishi Markandeshwar Engn Coll Elect & Commun Engn Dept Ambala Haryana India Chitkara Univ Chitkara Univ Inst Engn & Technol Dept Comp Sci & Engn Rajpura Punjab India Univ Bolton Sch Creat Technol Bolton England

Alzheimer's disease (AD) is a neurodegenerative disorder that mostly affects old aged people. Its symptoms are initially mild, but they get worse over time. Although this health disease has no cure, its early diagnosis can help to reduce its impacts. A methodology SMOTE-RF is proposed for AD prediction. Alzheimer's is predicted using machine learning algorithms. Performances of three algorithms decision tree, extreme gradient boosting (XGB), and random forest (RF) are evaluated in prediction. Open Access Series of Imaging Studies longitudinal dataset available on Kaggle is used for experiments. The dataset is balanced using synthetic minority oversampling technique. Experiments are done on both imbalanced and balanced datasets. Decision tree obtained 73.38% accuracy, XGB obtained 83.88% accuracy and RF obtained a maximum of 87.84% accuracy on the imbalanced dataset. Decision tree obtained 83.15% accuracy, XGB obtained 91.05% accuracy and RF obtained maximum 95.03% accuracy on the balanced dataset. A maximum accuracy of 95.03% is achieved with SMOTE-RF. machine learning algorithms namely Decision tree, XGB, and random forest are used for model building to predict Alzheimer's disease. Experiments are performed in two ways, first on the original dataset and then on class balanced datasets. As the dataset is highly imbalanced, the class imbalance problem is overcome by SMOTE technique. image

关键词： biomedical electronics computer vision feature extraction medical signal processing

来源：评论

学校读者我要写书评

暂无评论

Flotation Froth image Recognition Using vision Transformers 22

Flotation Froth Image Recognition Using Vision Transformers

引用

22nd World Congress of the International Federation of Automatic Control (IFAC)

作者： Liu, Xiu Aldrich, Chris Curtin Univ Western Australian Sch Mines Minerals Energy & Ch GPOB U1987 Perth WA 6845 Australia Univ Stellenbosch Dept Proc Engn Private Bag 11 ZA-7602 Stellenbosch South Africa

ISBN: (纸本)9781713872344

The application of computer vision systems on industrial flotation plants has benefited considerably from advances in deep learning over the last decade, mostly based on the use of convolutional neural networks and transfer learning. More recently, vision transformers (viTs) have attracted strong interest since their first appearance in 2017, compared to the popular convolutional neural networks (CNNs). Although becoming well-established in many areas, they have not yet been considered meaningfully in machine vision or signal processing applications in mineral processing, despite the obvious benefits that their application could realize. In this paper, it is demonstrated that viTs are neural network architectures highly capable of discriminating between different froth flotation images. A customized viT model and a pretrained viT model using transfer learning were studied and compared. The former achieved satisfactory performance and the latter achieved near perfect performance, both at a significantly lower computational cost than CNNs. These results suggest that viTs can be a competitive alternative to CNNs in the advancement of computer vision systems on industrial flotation plants. Copyright (c) 2023 The Authors.

关键词： vision transformer froth flotation froth image analysis deep learning transfer learning transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing public safety: a hybrid Conv_Trans-OptBiSvM approach for real-time abnormal behavior detection in crowded environments

引用

SIGNAL image AND vIDEO processing 2024年第11期18卷 7513-7525页

作者： valarmathi, v. Sudha, S. Sri Sairam Engn Coll Dept Informat Technol Chennai 600044 Tamil Nadu India Easwari Engn Coll Dept Elect & Commun Engn Chennai 600089 Tamil Nadu India

Abnormal behavior identification becomes significant in real-time smart environments as the act of threats is increasing globally, nowadays. Accurate recognition of abnormal behaviors well-ensures public safety and security, especially in crowded scenes, but is more complicated to estimate. The closed-circuit televisions (CCTvs) installed in public places to prevent crimes demand automated behavior modeling mechanisms to detect abnormal activities. The deep learning (DL) based computer vision algorithms although performing very well, are not capable of detecting abnormal behaviors in CCTv images in real-time due to the high computational complexity and ineffective learning behavior. To overcome this limitation, in our research, an intelligent 'Hybrid Conv_Trans-OptBiSvM' based abnormal behavior detection model is proposed. Diverse model components such as convolution backbone layer, spatial-temporal encoder and Attention in attention mechanism (A2M) are integrated for extracting complicated data patterns to identify the abnormal events in the image frames. The 2D-CNN layer extracts local and high-level features from the images. The encoder layer aims to identify global space and long-range temporal dependencies among adjacent pixels using self and cross-attention with temporal association. In addition, an A2M method assists in enhancing the quality of correlation map. It searches for correlation uniformity surrounding every key to improve the relevant correlations of corresponding key query pairs. Finally, classification is done by the designed optimized binary support vector machine (OptBiSvM). It uses particle swarm optimization (PSO) algorithm for tuning hyperparameters such as kernel parameter and cost parameter. We compare our model's performance with other algorithms to evaluate and validate its effectiveness using multiple benchmark datasets- UNM, UCSD (PED 1, PED2, and PETS 2009. The notable outcomes generated by the Hybrid Conv_Trans-OptBiSvM algorithm emph

关键词： Abnormal behavior detection CCTv images Convolutional neural network Particle swarm optimization Binary support vector machine Attention in attention Normal and abnormal

来源：评论

学校读者我要写书评

暂无评论

Stealing the Invisible: Unveiling Pre-Trained CNN Models Through Adversarial Examples and Timing Side-Channels

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2024年第4期14卷 634-646页

作者： Shukla, Shubhi Alam, Manaar Mitra, Pabitra Mukhopadhyay, Debdeep Indian Inst Technol Kharagpur Ctr Computat & Data Sci Kharagpur 721302 India New York Univ Abu Dhabi Ctr Cyber Secur Abu Dhabi U Arab Emirates Indian Inst Technol Kharagpur Comp Sci & Engn Dept Kharagpur 721302 India

machine learning, with its myriad applications, has become an integral component of numerous AI systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily available to the public, is fine-tuned to suit specific tasks. As machine Learning as a Service (MLaaS) platforms increasingly use pre-trained models in their backends, it is crucial to safeguard these architectures and understand their vulnerabilities. In this work, we present ArchWhisperer, a model fingerprinting attack approach based on the novel observation that the classification patterns of adversarial images can be used as a means to steal the models. Furthermore, the adversarial image classifications in conjunction with model inference times is used to further enhance our attack in terms of attack effectiveness as well as query budget. ArchWhisperer is designed for typical user-level access in remote MLaaS environments and it exploits varying misclassifications of adversarial images across different models to fingerprint several renowned Convolutional Neural Network (CNN) and vision Transformer (viT) architectures. We utilize the profiling of remote model inference times to reduce the necessary adversarial images, subsequently decreasing the number of queries required. We have presented our results over 27 pre-trained models of different CNN and viT architectures using CIFAR-10 dataset and demonstrate a high accuracy of 88.8% while keeping the query budget under 20. This is a marked improvement compared to state-of-the-art works.

关键词： Graphics processing units Predictive models Computer architecture Computational modeling Analytical models Fingerprint recognition Timing Convolutional neural networks Load modeling Integrated circuit modeling Model extraction attack trustworthy AI systems model fingerprinting adversarial attacks timing side-channel

来源：评论

学校读者我要写书评

暂无评论

Polarization image processing Technology Based on machine vision Detection

Polarization Image Processing Technology Based on Machine Vi...

引用

2023 International Conference on Big Data Mining and Information processing, BDMIP 2023

作者： Liu, Guoyan Zhao, Jincai Zeng, Yanan Wu, Haiyun Li, Zhi Wei, Yong College of Technology Tianjin Agricultural University Tianjin China

ISBN: (纸本)9798400709166

The detection and morphology characterization of these biological samples are the basis of life research. Optical microscopic imaging has great advantages in the characterization and detection of biological samples because of its characteristics of low sample requirements, good environmental adaptability, convenient, fast and non-destructive detection. However, due to the influence of optical diffraction limit, the resolution of optical microscopic imaging method is comparative low and thus limits the applications. Due to the polarization characteristics of the scattering field from scatterer are closely related to the microstructure of the scatterer, the measurement of the polarization characteristics of the scattering field can improve the detection and characterization ability of biological samples. Meanwhile, to achieve a higher resolution and to obtain a larger range of particle near-field scattering spectral distribution, the method in the paper takes the image acquisition part of the traditional machine vision system as the main body and a polarization modulation module is added to build an image acquisition device. The non-intuitive images obtained in the experiment are compared with the traditional direct imaging, and the results prove that the non-intuitive polarization parameter imaging can obtain the particle near-field scattering spectral distribution in a larger range than the traditional direct imaging. It is proved that non-intuitive light wave vectors are more sensitive to near-field scattering and have higher resolution. © 2023 ACM.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

3rd International Conference on machine vision and Augmented Intelligence, MAI 2023

3rd International Conference on Machine Vision and Augmented...

引用

3rd International Conference on machine vision and Augmented Intelligence, MAI 2023

ISBN: (纸本)9789819743582

The proceedings contain 76 papers. The special focus in this conference is on machine vision and Augmented Intelligence. The topics include: Survey on Robustness of Deep Learning Techniques on Adversarial Attacks in WBAN;synergizing Collaborative and Content-Based Filtering for Enhanced Movie Recommendations;exploring Transformer-Based Approaches for Hyperspectral image Classification: A Comparative Analysis;deep Learning for Cognitive Task and Seizure Classification with Hilbert–Huang Transform and variational Mode Decomposition;tracking of Ship and Plane in Satellite videos Using a Convolutional Regression Network with Deep Features;Tumor Detection and Analysis from Brain MRI images Using Deep Learning;software Maintenance Prediction Using Stack Ensemble Deep Learning Algorithms;resource Allocation in 6G Network for High-Speed Train Using D2D Outband Communication;controlling the Band-to-Band Tunneling Effect in Charge Plasma Based Dopingless Transistor;Comparison of Different CIC Filter Architectures on the Basis of a Novel Parameter Called Noise Factor for Sigma-Delta Based ADCs;the Scientific Analysis on Effective Yoga Posture Recognition Techniques;impact of Gamma Rays on Emerging Devices for Photonic applications;shaft Rotation Monitoring Using Radar Signal processing and Wavelet Transform;gysel Power Divider Miniaturization Using an Inter-Digital Capacitor-Based Slow-Wave Structure;noise Estimation and Removal in Fundus images Using Pyramid Real image Denoising Network;evaluation of Hybrid Encryption Method to Secure Healthcare Data;multimodal Face Recognition System Using Hybrid Deep Learning Feature;Classification of Copy and Move image by Using HELM-FSK Method: An Efficient Approach;analysis of Energy Efficient Smart Home Based on IoT System;role of Explainable Artificial Intelligence Approaches in Cybersecurity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FAST CODING MODE PREDICTION FOR INTRA PREDICTION IN vvC SCC 31

FAST CODING MODE PREDICTION FOR INTRA PREDICTION IN VVC SCC

引用

2024 International Conference on image processing

作者： Wang, Dayong Yu, Junyi Lu, Xin Dufaux, Frederic Guo, Hongwei Guo, Hui Zhu, Ce Chongqing Univ Posts & Telecommun Chongqing Key Lab Big Data Bio Intelligence Chongqing Peoples R China Wuzhou Univ Guangxi Key Lab Machine Vis & Intelligent Control Wuzhou Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongqing Peoples R China De Montfort Univ Fac Comp Engn & Media CEM Leicester Leics England Univ Paris Saclay CNRS Cent Supelec Lab Signaux & Syst Gif Sur Yvette France Honghe Univ Sch Engn Mengzi Yunnan Peoples R China Univ Elect Sci & Technol China Chengdu Sichuan Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Currently, screen content video applications are increasingly widespread in our daily lives. The latest Screen Content Coding (SCC) standard, known as versatile video Coding (vvC) SCC, employs screen content Coding Modes (CMs) selection. While vvC SCC achieves high coding efficiency, its coding complexity poses a significant obstacle to the further widespread adoption of screen content video. Hence, it is crucial to enhance the coding speed of vvC SCC. In this paper, we propose a fast mode and splitting decision for Intra prediction in vvC SCC. Specifically, we initially exploit deep learning techniques to predict content types for all CUs. Subsequently, we examine CM distributions of different content types to predict candidate CMs for CUs. We then introduce early skip and early terminate CM decisions for different content types of CUs to further eliminate unlikely CMs. Finally, we develop Block-based Differential Pulse-Code Modulation (BDPCM) early termination to improve coding speed. Experimental results demonstrate that the proposed algorithm can improve coding speed by 34.95% on average while maintaining almost the same coding efficiency.

关键词： vvC SCC content type fast coding mode decision BDPCM

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：