检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2024年 10卷 461-468页

作者： Huang, Ouwen Palmeri, Mark L. Duke Univ Dept Biomed Engn Durham NC 27708 USA

Handheld ultrasound devices are becoming more prevalent in point-of-care ultrasound workflows. However, these devices are computationally constrained which challenges the advances in deep learning methodology for real-time use on mobile Point-of-care ultrasound (POCUS) devices. In this work, we explore the feasibility of running MimickNet, a deep learning clinical post-processing model, on Tensor processing Units (TPUs), hardware designed for deep learning operations capable of running on only 2 watts of power at 1.8 V with a form factor of 10 mm x 15 mm. We show that real-time deep learning based post-processing is feasible at 20 - 120 FPS for 1472x160 to 224x224 axial sample x B-mode scan line configurations. We refer to the TPU based model as MimickNet Mobile. MimickNet Mobile achieves outputs nearly identical to the original MimickNet with a structural similarity index measurement (SSIM) of 0.98 +/- 0.001 and a mean squared error (MSE) of 0.0001 +/- 0.0 over our test set of 588 frames consisting of 168 phantom frames and 420 prospectively acquired human liver frames. We investigate the latency of other common mobile architectures such as separable convolution. Finally, we investigate the distribution of model parameter error when quantizing MimickNet float32 weights to MimickNet Mobile int8 weights. This work demonstrates that real-time POCUS deep learning image enhancement is feasible using TPUs. Future ultrasound device manufacturers can consider incorporating a TPU for the added flexibility of supporting several deep learning architectures without compromising on power management and form factor.

关键词： Clinical ultrasound deep learning image enhancement MimickNet real-time processing TPU

来源：评论

学校读者我要写书评

暂无评论

Integrating image processing Techniques with deep learning Network Models to Detect and Identify Defects on the Surface of Tomato

Integrating Image Processing Techniques with Deep Learning N...

引用

Electrical, Computer and Energy Technologies (ICECET), International Conference on

作者： Dinh Do van Sao Do University Hai Duong Viet Nam

Before export, fruit should be classified to improve quality, meet customer requirements and increase product value. This article proposes a method to identify defects on the surface of tomato skin using image processing techniques combined with deep learning models. The identification method includes the following main steps: (i) data collection (image of tomato: green, ripe, diseased, scratched), (ii) image labeling, (iii) data file division, (iv) model training, (v) selection and using models. The results of using Faster R-CNN model combining Resnet-10l and testing on YOLOv5 to identify and classify tomatoes that met and failed export for high accuracy (95.3 %) and met get real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of entertainment interactive robots based on deep learning in referee assistance mode in sports competitions

引用

ENTERTAINMENT COMPUTING 2025年 52卷

作者： Li, Xiaolong Shandong Univ Polit Sci & Law Student Affairs Off Jinan 250014 Shandong Peoples R China

Interactive robots are intelligent auxiliary tools that can monitor sports events in real-time and provide entertainment information services. This article studies the application of entertainment interactive robots based on deep learning in the referee assistance mode of sports competitions. The system first uses a camera to capture real-time images of volleyball matches, then preprocesses the images using image processing algorithms, and uses deep learning algorithms to recognize and track the balls and players in the images. By training the model, the system can accurately determine key information such as player actions. deep learning technology is used to train interactive entertainment robots to identify and analyze key decision events in games. Through image recognition, action analysis and rule matching, the robot monitors the game process in real time and determines the referee's possible errors in the decision. The system generates the penalty results based on the penalty rules and competition rules, and displays them to the referee and audience through display screens or sound prompts. After experimental verification, the volleyball match referee judgment assistance system based on image processing and deep learning has performed excellently in terms of accuracy and speed. Compared to manual referees, the system can identify and track the ball and players more quickly, reduce the possibility of misjudgments, and improve the fairness of the game.

关键词： deep learning Interactive robot for entertainment Sports competitions Referee auxiliary mode

来源：评论

学校读者我要写书评

暂无评论

image and Video Captioning Using deep learning and Natural Language processing

Image and Video Captioning Using Deep Learning and Natural L...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Manoj Naidu Athrva Kulkarni Sahil Kadam Siddhesh Joshi Nilesh P. Sable Anuradha Yenkikar Department of CSE – Artificial Intelligence Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

deep learning models have been a huge success in image recognition which hence can be used for the purpose of text generation. In the field of imaging science, captioning images and videos is regarded as an intellectually difficult job. Visual Geometry Group (VGG); is a standard deep Convolutional Neural Network (CNN) architecture with multiple layers, specifically focusing on the integration of CNN for image feature extraction. Exploring this underlying method, the use of another model is essential for caption generation. Here the Recurrent Neural Network (RNN) comes in use for caption generation from the extracted features. Models named Long Short-Term Memory (LSTM) based on RNN and Bidirectional encoder representation transformer (BERT) based on Transformers have been prominent in ensuring accurate results. The Flicker8k dataset is used which provides a variety of information useful for model training. By testing validation data along with evaluation metrics, we analyze the effectiveness of different models to create consistent and descriptive headlines. Extending our inquiry to encompass title generation using transformer models, while also exploring learning techniques for real-time title generation and delivery using the Open-CV library available in Python to get the output from the camera and display it on screen. The result shows that the LSTM is the best model for captioning, with an accuracy of 65.07% at the epochs of 300 and the BERT model has an accuracy of 31% at the epochs of 2. The findings of this study not only contribute to advancing subtitle enhancement methodologies but also broaden the potential applications of deep learning techniques in this domain.

关键词： deep learning Recurrent neural networks Accuracy Computational modeling Bidirectional control Transformers Feature extraction Encoding Data models Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Distributed deep learning for Medical image processing in Cloud Environments

Distributed Deep Learning for Medical Image Processing in Cl...

引用

Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： Neeraj Varshney Parul Madan Anurag Shrivastava C Praveen Kumar A Kakoli Rao Amit Srivastava Department of Computer Engineering and Applications GLA University Mathura Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad Telangana Lloyd Institute of Engineering and Technology Greater Noida Lloyd Law College Greater Noida

The incorporation of distributed deep learning for medical image processing in cloud settings is the subject of this study. The findings demonstrate the high viability and significant performance advantages realized by cloud-based distributed systems, notably significant processing time savings, outstanding diagnostic accuracy, as well as improved scalability. The consequences for security and privacy have been discussed, with a focus on effective safeguards for private medical information. There is a void in the literature about resource and cost-effectiveness optimization tactics used in cloud-based systems. Future research must concentrate on resource optimization tactics for economic sustainability, study developing security risks and privacy techniques, and incorporate real-world implementations in order to improve this topic. This study informs the use of distributed deep learning in cloud-based medical image processing as well as adds to the body of knowledge in healthcare technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of deep learning in MRI and CT Medical image processing 2021

An Overview of Deep Learning in MRI and CT Medical Image Pro...

引用

3rd International Symposium on Signal processing Systems, SSPS 2021

作者： Shomirov, Ahliddin Zhang, Jing School of Information Science and Engineering Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Shandong Jinan250022 China

ISBN: (纸本)9781450389587

The medical image is a set of all organizations, institutions, and resources whose primary goal is to improve health. The extensive growth of medical data increases the utility of machine learning and deep learning in the healthcare domains. Nowadays, the use of in-depth training to process medical images has received particular attention. In recent years, medical instruments have developed rapidly with the help of artificial intelligence and are widely used to process medical images. Artificial intelligence is numerous sources of medical imaging processing such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). CT and MRI image processing tasks with a high computation time requirement and computation speed. Nowadays, one of the most critical trends in the development of computer technology in neuroscience is the processing of medical images and digital images, which are used to improve image quality, restore damaged images, identify individual elements and diagnose various diseases. In this paper, we briefly review the progress and challenges associated with in-deep learning in the processing of CT and MRI medical images. © 2021 ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

MobileMEF: fast and efficient method for real-time mobile multi-exposure fusion

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-15页

作者： Kirsten, Lucas Nedel Fu, Zhicheng Madhusudhana, Nikhil Ambha Motorola Mobil Comercio Prod Eletron Ltda Jaguariuna SP Brazil Lenovo Res Chicago IL USA

Recent advances in camera design and imaging technology have enabled the capture of high-quality images using smartphones. However, due to the limited dynamic range of digital cameras, the quality of photographs captured in environments with highly imbalanced lighting often results in poor-quality images. To address this issue, most devices capture multi-exposure frames and then use some multi-exposure fusion method to merge those frames into a final fused image. Nevertheless, most traditional and current deep learning approaches are unsuitable for real-time applications on mobile devices due to their heavy computational and memory requirements. We propose MobileMEF, a new method for multi-exposure fusion based on an encoder-decoder deep learning architecture with efficient building blocks tailored for mobile devices. This efficient design makes MobileMEF capable of processing 4K resolution images in less than 2 s on mid-range smartphones. MobileMEF outperforms state-of-the-art techniques regarding full-reference quality measures and computational efficiency (runtime and memory usage), making it ideal for real-time applications on hardware-constrained devices. Our code is available at: https://***/LucasKirsten/MobileMEF.

关键词： image fusion Multi-exposure image real-time methods Smartphone photography

来源：评论

学校读者我要写书评

暂无评论

real-time image processing and deep learning 2019

Real-Time Image Processing and Deep Learning 2019

引用

real-time image processing and deep learning 2019

ISBN: (纸本)9781510626577

The proceedings contain 27 papers. The topics discussed include: fast multi-modal reuse: co-occurrence pre-trained deep learning models;deep learning for fast super-resolution reconstruction from multiple images;an efficient algorithm for fast block matching motion estimation using an adaptive threshold scheme;low exposure image frame generation algorithms for feature extraction and classification;parallel image and video self-recovery scheme with high recovery capability;learning optimal actions with imperfect images;CNN classification based on global and local features;kalman-based motion estimation in video surveillance systems for safety applications;and recent advances in integrated photonic-electronic technologies for high-speed processing and communication circuits for light-based transducers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cotton Leaf Disease Based on image processing Using deep learning

Cotton Leaf Disease Based on Image Processing Using Deep Lea...

引用

Innovations and Challenges in Emerging Technologies (ICICET), International Conference on

作者： D. Menaga B T Shri Roshan S R Shri Vikaas Department Of Computer Science and Engineering St. Joseph’s Institute of Technology Chennai India

ISBN: (数字)9798350319019

ISBN: (纸本)9798350319026

One of the most important occupations in India is agriculture. Out of all the crops, cotton is the best and is crucial to the agricultural economy of the country. In India, 40-50 million people work in the cotton trade and processing, while six million farmers directly depend on the crop. The cotton leaf disease has grown in importance over the last few decades, resulting in losses to crops, farming operations, and financial resources. To achieve this aim, we first need to acquire different images of cotton plants. We can use image processing techniques to analyze dead leaf images and extract features like color, texture, and other characteristics with the deep CNN model’s assistance. In addition to being less expensive and more straightforward, automatic disease detection supports machine vision, which offers image-based automated process control and inspection. To properly train the algorithm, we will be using a dataset of approximately 1752(approximately 440 images in each class) images classified into different categories according to the diseases. This model will be developed using tools present in Anaconda such as Jupyter Notebook, Spyder etc. The results of this project will demonstrate whether using it in real-time applications is feasible and whether traditional or manual disease and pest identification could benefit from the use of IT- based solutions.

关键词： Support vector machines Technological innovation Neural networks Crops Process control Feature extraction Vectors

来源：评论

学校读者我要写书评

暂无评论

Coffee Bean Defects Automatic Classification realtime Application Adopting deep learning

引用

IEEE ACCESS 2024年 12卷 126503-126517页

作者： Thai, Hong-Danh Ko, Han-Jong Huh, Jun-Ho Natl Korea Maritime & Ocean Univ Dept Data Informat Pusan 49112 South Korea Natl Korea Maritime & Ocean Univ Dept Interdisciplinary Major Ocean Renewable Energ Pusan 49112 South Korea Korea Natl Open Univ Dept Agr Sci Seoul 03087 South Korea Natl Korea Maritime & Ocean Univ Dept Data Sci Pusan 49112 South Korea

The coffee industry contributes to the economic restructuring of many countries, often associated with a closed process from production to consumption. The green coffee bean grading standard provided by the Specialty Coffee Association (SCA) is one of the best methods for grading coffee beans. Traditionally, the assessment of quality and classification of coffee beans relies on visual examination, which demands significant time and effort and is easily inaccurate. deep learning technology, characterized by precision, velocity, and veracity, can be adopted to empower the reduction of human labor and improve the productivity, quality, and efficiency of these tasks. Therefore, this paper aims to address these issues by implementing deep learning to classify coffee bean quality in real time by integrating the system with a cloud-based solution. First, image processing and data augmentation techniques are employed to handle the coffee bean image data. Subsequently, the model is trained using YOLOv8, a framework for object recognition, and OpenCV, an open-source image processing technology, to classify coffee beans. Finally, an application is developed for real-time video and image-streaming coffee bean recognition using React Native, NodeJS, and Python. The experimental results provide empirical evidence that our system enhances accuracy and efficiency in the tasks of classifying coffee bean quality in nine distinct varieties of coffee beans, with the time required reduced to a mere 1 to 3 seconds. Our system can be a useful solution for coffee producers, processors, and traders without relying on stationary equipment, especially in large farms or warehouses.

关键词： deep learning Classification algorithms real-time systems Accuracy Nearest neighbor methods image processing Crops Defect detection YOLO Cloud computing Economics Coffee bean defects quality classification computer vision YOLOv8 OpenCV cloud-based application deep learning

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：