检索结果-内蒙古大学图书馆

IEEE International Conference on image processing

作者： Maniratnam Mandal Neil Birkbeck Balu Adsumilli Alan C. Bovik University of Texas at Austin YouTube Google Inc

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

User-generated content (UGC) is ubiquitous across the internet as a result of billions of videos and images being uploaded each day. All kinds of UGC media are affected by natural distortions, occurring both during and after capture, which are inherently diverse and commingled. These distortions have different perceptual effects based on the media content. Given recent dramatic increases in the consumption of short-form content, the analysis and control of their perceptual quality has become an important problem. Regardless of the content, many UGC videos have overlaid and embedded texts in them, which are visually salient. Hence text quality has a significant impact on the global perception of video or image quality and needs to be studied. One of the most important factors in perceptual text quality in user-generated media is legibility, which has been studied very little in the context of computer vision. Predicting text legibility can also help in text recognition applications such as image search or document identification. This work aims at modeling text legibility using computer vision techniques and thus studying the relationship between text quality and legibility. We propose a modified dataset variant of COCO-Text [1] and a model for predicting text legibility for both handwritten and machine-generated texts. We also demonstrate how models trained to predict text legibility can help in the prediction of text (perceptual) quality. The dataset and models can be accessed here https://***/research/Quality/***.

关键词： image quality Computer vision Text recognition Computational modeling User-generated content Media Predictive models

来源：评论

学校读者我要写书评

暂无评论

Computer vision Based Hybrid Classroom Attention Monitoring

Computer Vision Based Hybrid Classroom Attention Monitoring

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Saniya Rawat Malivia Rodrigues Prateeksha Sheregar Kalpita Ajinkya Wagaskar Amiya Kumar Tripathy Department of Computer Engineering Don Bosco Institute of Technology Mumbai India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

This research presents a novel computer vision-based attention monitoring system designed for both online and offline contexts. Leveraging advanced image processing and machine learning algorithms, the system analyzes human gaze patterns, eye movements, and facial expressions to accurately gauge attention levels. In online scenarios, the system employs real-time webcam-based gaze tracking and facial recognition to provide immediate insights into user engagement during activities like video conferencing and virtual meetings. For offline analysis, recorded video footage is retrospectively examined, facilitating applications in education, workplace productivity, and user experience assessments. Privacy considerations are addressed through the implementation of privacy-preserving techniques. Experimental results demonstrate the system's efficacy in monitoring attention dynamics across diverse settings, contributing to a deeper understanding of human attention in various domains.

关键词： image processing Face recognition Education Gaze tracking Web conferencing Streaming media Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Patch-Attention GAN: image Translation using BiFormer and Attention Framework

Patch-Attention GAN: Image Translation using BiFormer and At...

引用

Computer vision, image and Deep Learning (CVIDL), International Conference on

作者： Dingwen Xiao Huiqing Wu School of Science The Hong Kong University of Science and Technology Hong Kong China Faculty of Science and Technology BNU-HKBU United International College Zhuhai China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

image-to-image translation has long been recognized as a crucial undertaking within the field of computer vision, owing to its broad applications in domain adaption. Existing methods differ in Generative Adversarial Network framework and model structure. Attention-Guided training framework absorbs the input image’s semantic information based on the translation task. However, it ignores the local context for content extraction and lacks mask comparison in the loss function. The attention mechanism is widely regarded as an effective approach for addressing contextual challenges in machine learning models. By augmenting the model’s capacity to capture long-range dependencies and concentrate on the most salient aspects of the input sequence, the attention mechanism significantly enhances its contextual understanding. Bi-level routing attention stands out among other mechanisms for its computation speed and memory cost. In this paper, we propose an image translation algorithm called Patch-Attention Generative Adversarial Network that combines foreground-background separation processing, bi-level routing attention, and content loss. Our proposed method has been extensively evaluated on diverse datasets, yielding compelling experimental results. These findings demonstrate the substantial performance boost achieved by our approach in the domain of image translation. The generated image is more clarified and understandable compared with other existing approaches.

关键词： Training Computer vision Visualization Attention mechanisms Computational modeling Semantics Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv8 Orchard Fruit Object Detection Algorithm Based on Enhanced Feature Fusion

Improved YOLOv8 Orchard Fruit Object Detection Algorithm Bas...

引用

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

作者： Zengming Li Haihui Lu Shuyuan Yang Wenjian Zhang Jianming Mo Zilu Zhou Shufei Huang Shijing Feng Kaijun Luo Xingjun Lin School of Modern Information Industry Guangzhou College of Commerce Huangpu China School of Information Technology & Engineering Guangzhou College of Commerce Huangpu China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Smart agriculture is becoming increasingly popular with the development of computer and artificial intelligence technology. The use of artificial intelligence technology to improve orchard management and enhance harvesting efficiency is an important technology. The current target detection algorithms based on YOLO can preliminarily complete the construction of the system. However, in these detection methods, the feature fusion part did not fully consider the actual contribution differences of different resolution feature maps to the final output, which may become a performance bottleneck when dealing with targets of different sizes and complexities. In response to the above issues, this article proposes an orchard fruit object detection algorithm based on improved YOLOv8. This algorithm improves the feature fusion part in YOLOv8 by introducing the BiFPN (Bidirectional Feature Pyramid Network) module. This method improves the accuracy and efficiency of the model in detecting objects of different sizes through a more refined feature fusion strategy. Through experiments, it has been proven that the proposed algorithm significantly improves the accuracy of object detection while ensuring computational efficiency, especially when dealing with challenging multi-scale objects. The improved algorithm improved accuracy by 16.5 percentage points, recall by 23.3 percentage points, mAP50 by 16.5 percentage points, and mAP50-95 by 20 percentage points on the avocado dataset. This research achievement has promoted the development of YOLOv8 in terms of performance in practical applications from a new perspective, and laid the foundation for future research on object ***.

关键词： YOLO Smart agriculture Accuracy image recognition machine learning algorithms Target recognition Face recognition machine learning Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Railroad Sleeper Condition Monitoring Using Non-Contact in Motion Ultrasonic Ranging and machine Learning-Based image processing

引用

SENSORS 2023年第6期23卷 3105-3105页

作者： Datta, Diptojit Hosseinzadeh, Ali Zare Cui, Ranting di Scalea, Francesco Lanza Univ Calif San Diego Dept Struct Engn NDE & SHM Lab Expt Mech La Jolla CA 92093 USA Guangxi Univ Coll Civil Engn & Architecture Nanning 530004 Peoples R China

An ultrasonic sonar-based ranging technique is introduced for measuring full-field railroad crosstie (sleeper) deflections. Tie deflection measurements have numerous applications, such as detecting degrading ballast support conditions and evaluating sleeper or track stiffness. The proposed technique utilizes an array of air-coupled ultrasonic transducers oriented parallel to the tie, capable of "in-motion" contactless inspections. The transducers are used in pulse-echo mode, and the distance between the transducer and the tie surface is computed by tracking the time-of-flight of the reflected waveforms from the tie surface. An adaptive, reference-based cross-correlation operation is used to compute the relative tie deflections. Multiple measurements along the width of the tie allow the measurement of twisting deformations and longitudinal deflections (3D deflections). Computer vision-based image classification techniques are also utilized for demarcating tie boundaries and tracking the spatial location of measurements along the direction of train movement. Results from field tests, conducted at walking speed at a BNSF train yard in San Diego, CA, with a loaded train car are presented. The tie deflection accuracy and repeatability analyses indicate the potential of the technique to extract full-field tie deflections in a non-contact manner. Further developments are needed to enable measurements at higher speeds.

关键词： railroad sleeper monitoring ultrasonic ranging digital signal processing machine learning and image processing nondestructive evaluation

来源：评论

学校读者我要写书评

暂无评论

Role of Thermal images in Various applications of Computer vision

Role of Thermal Images in Various Applications of Computer V...

引用

Intelligent Engineering and Management (ICIEM), International Conference on

作者： Ravina Gupta Sarika Jain Manoj Kumar AIIT Amity University Noida India EIS University of Wollongong Dubai

Object detection is an advanced area of image processing and computer vision. Its major applications are in surveillance, autonomous driving, face recognition, anomaly detection, traffic management, agriculture etc. This paper focuses on various object detection techniques in thermal images. A thermal imaging sensor is a device that creates an image by analyzing temperature differences between different objects in a scene and detecting radiation from those objects. In recent years, many machine learning and deep learning algorithms have been used to recognize objects in thermal images. This study makes a comparison of YOLO, YOLO DarkNet, Retinex algorithm, CNN-based machine learning model Support Vector machine (SVM), and Gaussian Mixture Model (GMM), Mixer of Gaussian (MoG), Mean Shift Approach, Faster R-CNN and Deep Neural Network along with different datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Methodological Review on Prediction of Multi-Stage Hypovigilance Detection Systems Using Multimodal Features

引用

IEEE ACCESS 2021年 9卷 47530-47564页

作者： Abbas, Qaisar Alsheddy, Abdullah Imam Muhammad Ibn Saud Islamic Univ IMSIU Coll Comp & Informat Sci Riyadh 11432 Saudi Arabia

Several hypovigilance detection systems (HDx) were developed to avoid road-side accidents due to driver fatigue. They have suffered from several limitations. Notably many of these are focused on center-head position to define an area of interest (often referred to as PERCLOS (percentage eye closure)) without considering the face occlusion problem, light illumination, and suffer poor response time. These HDx systems mostly depend on image processing, vision-based, and multisensor-based features. To address these problems, the author utilized vision, sensors, environmental, and vehicular-based features that integrated together by fusion to predict multistage of HDx. Lately, few studies have utilized the combination of multimodal features and deep learning (DL) architectures. Those multimodal-based features (M-HDx) were feasible to predict stages of driver fatigue (multi-stage). However, there is a need to critically measure the performance of these M-HDx by carrying out a comparative analysis to recognize multi-stage of fatigue in terms of hardware-based benchmarks. Moreover, it is important to evaluate the M-HDx systems using different features-set with respect to traditional and advanced machine learning techniques. Therefore, the primary aim of this work is in algorithm and feature modeling, then compare the advantages and differences with other work. In this paper, a different study is conducted compare to state-of-the-art survey articles by statistically measuring the performance. After experiments on M-HDx systems, this paper concludes that there is still a research gap to real-time development of multistage M-HDx systems. In the end, the paper summarizes the directions, challenges, and applications in the development of HDx systems to assist other researchers for further research.

关键词： Vehicles Fatigue Feature extraction Real-time systems Protocols Monitoring machine learning algorithms Computer vision driver hypovigilance driver distraction deep learning hybrid learning models multimodal features machine learning multisensor fusion transfer learning

来源：评论

学校读者我要写书评

暂无评论

CSIM: A COPULA-BASED SIMILARITY INDEX SENSITIVE TO LOCAL CHANGES FOR image QUALITY ASSESSMENT

arXiv

引用

arXiv 2024年

作者： El Ghazouali, Safouane Michelucci, Umberto El Hillali, Yassin Nouira, Hichem TOELT LLC AI lab Winterthur Switzerland Polytechnique Haut-de-France Valenciennes France LNE-CNAM Paris France

image similarity metrics play an important role in computer vision applications, as they are used in image processing, computer vision and machine learning. Furthermore, those metrics enable tasks such as image retrieval, object recognition and quality assessment, essential in fields like healthcare, astronomy and surveillance. Existing metrics, such as PSNR, MSE, SSIM, ISSM and FSIM, often face limitations in terms of either speed, complexity or sensitivity to small changes in images. To address these challenges, a novel image similarity metric, namely CSIM, that combines real-time while being sensitive to subtle image variations is investigated in this paper. The novel metric uses Gaussian Copula from probability theory to transform an image into vectors of pixel distribution associated to local image patches. These vectors contain, in addition to intensities and pixel positions, information on the dependencies between pixel values, capturing the structural relationships within the image. By leveraging the properties of Copulas, CSIM effectively models the joint distribution of pixel intensities, enabling a more nuanced comparison of image patches making it more sensitive to local changes compared to other metrics. Experimental results demonstrate that CSIM outperforms existing similarity metrics in various image distortion scenarios, including noise, compression artifacts and blur. The metric’s ability to detect subtle differences makes it suitable for applications requiring high precision, such as medical imaging, where the detection of minor anomalies can be of a high importance. The results obtained in this work can be reproduced from this Github repository: https://***/safouaneelg/copulasimilarity. © 2024, CC BY-SA.

关键词： image quality

来源：评论

学校读者我要写书评

暂无评论

Preprocessing to improve the accuracy of recognition of radioelement components in automated assembly devices 9

Preprocessing to improve the accuracy of recognition of radi...

引用

Conference on Optical Metrology and Inspection for Industrial applications IX Part of SPIE/COS Photonics Asia Conference

作者： Semenishchev, Evgeny A. Zelensky, Aleksandr Zdanova, Marina Sizyakin, Roman Ilukhin, Yuriy Voronin, Viacheslav Tula State Univ TulSU Lab Cognit Technol & Simulat Syst 92 Sq Lenina Tula 300012 Tula Region Russia Moscow State Tech Univ STANKIN Ctr Cognit Technol & Machine Vis 1a Vadkovsky Moscow 127055 Russia

ISBN: (纸本)9781510657052;9781510657045

The article presumes a data processing algorithm that improves the accuracy of recognition of radio-electronic components in devices for automated installation. The paper proposes the use of a multicriteria filtering method that allows you to automatically change the smoothing coefficient. Varying the coefficient allows both reducing the noise component and preserving the boundaries of the radio elements without blurring. In order to enhance the contours of objects, a data simplification method is applied using the technique of reducing the range of clusters of color gradient histograms while preserving the shapes of objects. At the stage of detecting the boundaries of the elements and forming the structure of the elements of the radio component base, a modified one-dimensional two-criteria method is used. The combined analytical approach allows detection of the boundaries of radioelements and increases the productivity of the process. As test data used to evaluate the effectiveness, pairs of test images obtained by sensors fixed at various magnifications with a resolution of 1024x768 (8 bit, color image, visible range) are used. images of simple shapes are used as analyzed objects.

关键词： control systems preprocessing machine vision electronics radioelement robotic system

来源：评论

学校读者我要写书评

暂无评论

Automated Fundus image Standardization Using a Dynamic Global Foreground Threshold Algorithm

Automated Fundus Image Standardization Using a Dynamic Globa...

引用

International Conference on image, vision and Computing (ICIVC)

作者： Riley Kiefer Muhammad Abid Mahsa Raeisi Ardali Jessica Steen Ehsan Amjadian Department of Computer Science Florida Polytechnic University Lakeland FL US College of Optometry Nova Southeastern University Fort Lauderdale FL USA Cheriton School of Computer Science University of Waterloo Waterloo Ontario Canada

A generic fundus foreground extractor is required for the standardization of fundus datasets in machine-learning applications due to the vast range of retinal fundus images. Some fundus images have a large amount of non-essential background data and others have missing data because of clipping. To standardize these varied images for machine learning applications while preserving the aspect resolution, a generalized threshold algorithm is needed to separate the foreground and background. Existing threshold algorithms fail to segment images with low contrast. There is a need for a generalized algorithm to handle varied image conditions in a dynamic manner. The proposed segmentation algorithm uses shifts in histogram frequency using intensity extrema to find the ideal threshold value. The proposed post-processing algorithm crops, pads, and resizes the image to a standardized size of 512x512 pixels using the segmentation map output. To demonstrate the effectiveness of this proposed standardization approach on downstream tasks, an ablation experiment of popular standardization strategies is evaluated on a newly proposed benchmark dataset, EyePACS-light. The experimental results demonstrate the benefits of using this standardization approach for resizing fundus images.

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：