检索结果-内蒙古大学图书馆

作者： Chen, Tianlang University of Rochester

学位级别：Ph.D., Doctor of Philosophy

With the development of computer vision, natural language processing, and machine learning technologies, a great number of joint visual-textual applications, such as image captioning, visual question answering, visual grounding, image-text cross-modal retrieval, and text-based image generation, emerged in recent years. They leverage machine learning models as the core module to tackle problems related to the intersection of vision and language. For all these joint visual-textual applications, vision and text modalities interact in three fundamental modes. The first is the "joint learning" mode, which considers both modalities as parallel inputs to jointly predict a target. The second is the "retrieval" mode, which explores the correspondence relation between the two modalities and aims to find the corresponding items that belong to different modalities. The third is the "generation" mode, which focuses on creating and modifying the items of one modality using the input of another modality as guidance. For all the joint visual-textual applications of the three modes, how to effectively "capture" and "attend" to the significant information of the visual and textual inputs is crucial. This thesis develops new "capturing" and "attending" methods to effectively model joint visual-textual applications in the three modes. For the first mode, we focus on a significant social media classification application. A novel bilateral attention model is proposed to classify whether a WeChat Moment is related to business or not based on the Moment's image and text information. For the second mode, we comprehensively investigate the application of image-text cross-modal retrieval on both general and domain-specific tasks. We first explore the general image-text matching task and propose approaches that capture high-performance cross-modal information. We then focus on two domain-specific tasks related to font retrieval and person search. We design methods to further utilize the specia

关键词： Computer vision Joint visual-textual application Joint visual-textual modeling Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Design of a Secure image Sensor with Dynamic Reconfiguration

引用

JOURNAL OF SIGNAL processing SYSTEMS FOR SIGNAL image AND VIDEO TECHNOLOGY 2020年第9期92卷 999-1015页

作者： Bhowmik, Pankaj Pantho, Md Jubaer Hossain Bobda, Christophe Univ Florida Dept Elect & Comp Engn Gainesville FL 32611 USA

This paper presents a secure reconfigurable hierarchical hardware architecture at the pixel and region level for smart image sensors to accelerate machine vision applications. The design maintains hierarchical processing that begins at the pixel level. It aims to reduce the computational burden on the sequential processor and increases the confidentiality of the sensor. We achieve this goal by preprocessing the data in parallel with event-based processing within the sensor and extract the local features, which are then forwarded to an encryption module. After that, an external processor can obtain the encrypted features to complete the vision application. This approach significantly accelerates the vision application by executing the low-level and mid-level image processing applications and simultaneously by reducing the data volume at the sensor level. The secure hardware architecture enables the vision application to perform in real-time with reliability. This hierarchical processing breaks the traditional sequential image processing and introduces parallelism for machine vision applications. We evaluate the design in FPGA and achieve the GDSII file in the ASIC platform at 800MHz. Simulation results show that the area overhead and power penalty for adding reconfiguration features stay in an acceptable range. Besides, removing redundant information, 84.01%, and 94.31% dynamic power can be saved at each pixel-level and region-level, respectively.

关键词： Pixel level processing Reconfigurability Predictive coding Attention module image encryption Secure image sensor FPGA ASIC

来源：评论

学校读者我要写书评

暂无评论

Traffic Management System Using Computer vision 5th

Traffic Management System Using Computer Vision

引用

5th International Conference on Recent Trends in machine Learning, IoT, Smart Cities, and applications, ICMISC 2024

作者： Jeslin Shanthamalar, J. Yuthika, P. Kannan, R. Albert Mayan, J. Velvizhi, R. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India

ISBN: (纸本)9789819788644

It is essential to find creative solutions to the growing urban problems of traffic congestion and parking issues. By using real-time traffic camera photos with image processing and deep learning algorithms to compute traffic density in real-time, the suggested approach gets around these problems. The system speeds up transit and lowers pollution in megacities by reducing traffic dramatically and dynamically modifying traffic lights based on vehicle density. The study also presents a novel solution to the issue of people circling open lots in search of parking spots. The system achieves a remarkable positive detection rate by using thermal cameras and cutting-edge deep learning architectures using Yolov4. The overall accuracy of the YOLO v4 model in this hypothetical scenario is approximately 0.90. Parking lot cruising patterns are illuminated by the precise tracking of several moving automobiles made possible by Kalman filters. In addition to improving traffic control, this combination of state-of-the-art technologies provides insightful information about parking behavior, opening the door to more effective urban mobility solutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

CD-SEM Anomaly Detection Through machine Learning and Generative AI

CD-SEM Anomaly Detection Through Machine Learning and Genera...

引用

IEEE/SEMI Conference and Workshop on Advanced Semiconductor Manufacturing

作者： Susan Sun Xiaoyan Zhuo Phong Nguyen Todd Smith Jinhua Ding Troy Stansell Amit Srivastava Yousef Hanif Data Science Micron Technology Inc. Manassas VA USA Lithography Process Eng Micron Technology Inc. Manassas VA USA Data Science Micron Technology Inc. Singapore Product Quality Assurance Micron Technology Inc. Manassas VA USA

ISBN: (数字)9798331531850

ISBN: (纸本)9798331531867

In a complex semiconductor manufacturing environment, critical dimension scanning electron microscope (CD-SEM) images are captured at metrology step to monitor structural measurements and detect anomaly to meet the stringent process control requirements. This paper focuses on advanced CD-SEM image processing and anomaly detection using machine learning and generative AI models, which include computer vision (CV) image processing, Residual Neural Network (ResNet) deep learning and Generative Adversarial Network (GAN) model for various use cases. The applications of these models during in-line monitoring are crucial to identify potential process issues for yield and quality improvement.

关键词： Deep learning Semiconductor device measurement Generative AI image processing Computational modeling Semiconductor device manufacture Generative adversarial networks Servers Anomaly detection Monitoring

来源：评论

学校读者我要写书评

暂无评论

Product Digital Quality Inspection using machine vision Systems - A Categorical Review 17

Product Digital Quality Inspection using Machine Vision Syst...

引用

17th Annual System of Systems Engineering Conference, SOSE 2022

作者： Reyna, Mark Delgado, Guadalupe Akundi, Aditya Luna, Sergio Chumacero, Erik University of Texas Rio Grande Valley Complex Engineering Systems Laboratory BrownsvilleTX United States University of Texas Rio Grande Valley Dept. of Manufacturing and Industrial Engineering EdinburgTX United States University of Texas Rio Grande Valley Dept. of Informatics and Engineering Systems BrownsvilleTX United States University of Texas at El Paso El Industrial Manufacturing and Systems Engineering Dept El PasoTX United States

ISBN: (纸本)9781665496230

A key element of quality control in manufacturing is Product Inspection, which is a process that allows for verifying a product's quality enabled by activities such as measuring, examining, and testing one or more characteristics of a product. Automated machine vision systems undertake this task for in-line, in-process inspections. machine vision (MV) technology is designed to imitate the human visual system. The ability for computers to see the world through cameras and analyze their findings autonomously, often through deep learning, is making MV a market-disrupting technology. Many manufacturers seek to adopt this technology to improve production rates, product quality, and lower costs. The focus of this paper is to review the MV systems being developed to handle quality control, specifically product inspection tasks for various manufacturing applications. We present recently developed MV systems that perform product inspection based on free-form analysis, dimensional analysis, and surface analysis. Further, a discussion is provided to address the commonalities found in MV systems and the challenges the technologies continue to face. Additionally, each product quality inspection technique is examined for image processing techniques used. © 2022 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Colour based Object Classification using KNN Algorithm for Industrial applications 1

Colour based Object Classification using KNN Algorithm for I...

引用

1st IEEE International Conference on Automation, Computing and Renewable Systems, ICACRS 2022

作者： Santosh Kumar, N.C. Uma Maheswari, S. Vigneshwari, M. Pramila, P.V. Khilar, Rashmita Kumar, Ashok Department of Computer Science Engineering Kakatiya Institute of Technology and Science Telangana Warangal India Department of Electronics and Communication Engineering Panimalar Engineering College India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha Schoolof Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Information Technology Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Computer Science Banasthali Vidyapith Rajasthan India

ISBN: (纸本)9781665460842

Object classification and detection involve numerous applications like image processing, picture retrieval, security and surveillance, video communication, robot vision and observation. They are often classified based on their properties like colour, shape, quality and texture. However, their accuracy is mostly predicted by colour recognition. Colour based detection of objects has a discriminating quality to detect an object of any primary colour. The extraction of two or three-dimensional objects based on colour plays a vital role in real-time image processing technology. This review paper proposes the method for colour-based object classification applied in the lays industry using the 'K-nearest neighbour algorithm' which is the simplest form of machine learning classification method. The ML model is designed in such a way that once the colour of the lays pack is detected it also specifies its particular flavour. Hence for efficient machine-based colour identification in industries, this method would be an appropriate one and can be used for many other applications. © 2022 IEEE

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

ROT-Harris: A Dynamic Approach to Asynchronous Interest Point Detection 17

ROT-Harris: A Dynamic Approach to Asynchronous Interest Poin...

引用

17th International Conference on machine vision applications (MVA)

作者： Harrigan, S. Coleman, S. Ker, D. Yogarajah, P. Fang, Z. Wu, C. Ulster Univ Sch Comp Engn & Intelligent Syst Londonderry BT48 0QR North Ireland Northeastern Univ Fac Robot Sci & Engn Shenyang 110169 Liaoning Peoples R China

ISBN: (纸本)9784901122207

Event-based vision sensors are a paradigm shift in the way that visual information is obtained and processed. These devices are capable of low-latency transmission of data which represents the scene dynamics. Additionally, low-power benefits make the sensors popular in finite-power scenarios such as high-speed robotics or machine vision applications where latency in visual information is desired to be minimal. The core datatype of such vision sensors is the 'event' which is an asynchronous per-pixel signal indicating a change in light intensity at an instance in time corresponding to the spatial location of that sensor on the array. A popular approach to event-based processing is to map events onto a 2D plane over time which is comparable with traditional imaging techniques. However, this paper presents a disruptive approach to event data processing that uses a tree-based filter framework that directly processes raw event data to extract events corresponding to interest point features, which is then combined with a Harris interest point approach to isolate features. We hypothesise that since the tree structure contains the same spatial information as a 2D surface mapping, Harris may be applied directly to the content of the tree, bypassing the need for transformation to the 2D plane. Results illustrate that the proposed approach performs better than other state-of-the-art approaches with limited compromise on the run-time performance.

关键词： Performance evaluation Visualization Interest point detection machine vision Detectors vision sensors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ADMC: An Attention-based Dense Multi-scale Convolutional architecture for Medical image Segmentation

ADMC: An Attention-based Dense Multi-scale Convolutional arc...

引用

image processing, Computer vision and machine Learning (ICICML), International Conference on

作者： Zhao Hao Harbin University of Science and Technology Harbin China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Medical image segmentation is crucial for many healthcare applications, and deep learning networks have shown great potential in performing semantic segmentation tasks effectively. However, existing methods often suffer from the loss of important local features. To solve this problem, We introduce an innovative approach: a multi-scale and multi-connection feature adaptive fusion method guided by an attention mechanism. The proposed method emphasizes adaptive fusion of multi-scale and multi-connection features, effectively capturing meaningful features at different scales, while also utilizing attention mechanism to enhance feature representation. Specifically, Our approach leverages dense multi-scale skip connections to bridge the semantic gap between the feature maps of the encoder and decoder, where the feature map in each decoder module is connected with each feature map in encoder module. Besides, our network incorporates a deep attention block (DCS) in the encoder to capture meaningful local features. In the decoder, we introduce an efficient multi-scale convolution block (MSDC) to refine feature maps by performing deep convolution across multiple scales. Experimental results in the well known The ISIC dataset results demonstrate that our approach significantly outperforms the baseline method in the task of medical image segmentation.

关键词： image segmentation Attention mechanisms Convolution Semantic segmentation Semantics Refining Computer architecture Feature extraction Decoding Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Developments in Text Extraction from images: Comparative Evaluation of Various Techniques

Developments in Text Extraction from Images: Comparative Eva...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Akash Burnwal Nishi Choudhary Saurav Kumar Mamata P. Wagh Hrishika Computer Science And Engineering C.V. Raman Global University Bhubaneswar India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Extracting text from images is essential in image processing and computer vision, with applications in document digitization and automated text recognition. This paper reviews various text extraction techniques, categorized into thresholding, rough set and fuzzy set methods, clustering, edge detection, and machine learning. Thresholding techniques such as Gaussian, Otsu, adaptive, and double-edge methods are explored. Rough set and fuzzy set methods, which handle uncertainty in image data and improve text segmentation, are reviewed. Clustering techniques, such as K-means and density-based methods, are studied for their effectiveness in grouping pixels for text isolation. Edge detection techniques, including Sobel, Roberts, Canny, Morphological Component Analysis (MCA), and Laplacian, are examined for their role in enhancing text boundary identification. machine learning approaches, such as Support Vector machines (SVM), Contrastive Language-image Pre-training (CLIP), Hidden Markov Models (HMM), and hybrid BiLSTM-CNN models, are analyzed for their ability to improve accuracy in noisy environments. This review compares these techniques, highlighting their strengths, challenges, and applications for text extraction.

关键词： Support vector machines Fuzzy sets Thresholding (Imaging) Accuracy Text recognition Reviews image edge detection Hidden Markov models Rough sets machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Trajectory Planning Algorithm for Moving Measuring Instrument for Binding a Basic Coordinate System Based on a machine vision System

Development of a Trajectory Planning Algorithm for Moving Me...

引用

International Conference on Industrial Engineering, applications and Manufacturing (ICIEAM)

作者： Nataliya Krotova Roman Pushkov Svetlana Evstafieva Department of Computer Control Systems MSUT "STANKIN" Moscow Russian Federation

This article describes a solution for automating measurements on CNC machines equipped with automatic measurement tools using a vision system that simulates stereoscopic vision. The proposed method of measurement allows non-contact determination of the approximate position of the workpiece on the machine to fill in the parameters of measuring cycles. A three-stage algorithm for image processing by a software module of such a system is described, including recognition of the area with the workpiece, automatic correction of input images for successful contour recognition, determining of the contours of the workpieces and their geometric parameters, as well as calculation of the approximate dimensions of the workpieces relatively to the marks applied to the machine worktable beforehand. The calculated dimensions must be transmitted to the CNC system of the machine to run a parameterized program that calls a measuring cycle that clarifies the position of the workpiece on the machine. A model of the vision system has been implemented and tested.

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：