检索结果-内蒙古大学图书馆

A NONLOCAL KRONECKER-BASIS-REPRESENTATION METHOD FOR LOW-DOSE CT SINOGRAM RECOVERY

Journal of Computational Mathematics 2024年第4期42卷 1080-1108页

作者： Jian Lu Huaxuan Hu Yuru Zou Zhaosong Lu xiaoxia Liu Keke Zu Lin Li Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China National Center for Applied Mathematics Shenzhen(NCAMS) Shenzhen 518055China Department of Industrial and Systems Engineering University of Minnesota Twin CitiesMinneapolisMN55455USA Department of Applied Mathematics The Hong Kong Polytechnic UniversityHong Kong SARChina School of Electronic Engineering Xidian UniversityXi'an 710071China

Low-dose computed tomography(LDCT)contains the mixed noise of Poisson and Gaus-sian,which makes the image reconstruction a challenging *** order to describe the statistical characteristics of the mixed noise,we adopt the sinogram preprocessing as a stan-dard maximum a posteriori(MAP).Based on the fact that the sinogram of LDCT has non-local self-similarity property,it exhibits low-rank *** conventional way of solving the low-rank problem is implemented in matrix forms,and ignores the correlations among similar patch *** avoid this issue,we make use of a nonlocal Kronecker-Basis-Representation(KBR)method to depict the low-rank problem.A new denoising model,which consists of the sinogram preprocessing for data fidelity and the nonlocal KBR term,is developed in this *** proposed denoising model can better illustrate the generative mechanism of the mixed noise and the prior knowledge of the ***-merical results show that the proposed denoising model outperforms the state-of-the-art algorithms in terms of peak-signal-to-noise ratio(PSNR),feature similarity(FSIM),and normalized mean square error(NMSE).

关键词： Low-dose computed tomography Kronecker-basis-representation Low-rank imation.Noise-generating-mechanism

来源：评论

学校读者我要写书评

暂无评论

Fired:An image-Based Fire Detector for Smart Homes using Machine Learning algorithms

Fired:An Image-Based Fire Detector for Smart Homes using Mac...

引用

2024 International conference on Knowledge Engineering and Communication systems, ICKECS 2024

作者： Srinath, G.M. Yashaswini, K.M. Sahana Shree, N. Supraja, B. Varshitha, V. Arfa Thareen, K. Visvesvaraya Technological University Department of Computer Science and Engineering Chickballapur India

ISBN: (纸本)9798350359688

Smart homes are to be protected from fire hazards which is a crucial safety concern. Existing ways of detecting fire is time consuming, hence causing maximum injuries and financial loss, so we have come up with an effective solution for detecting fire in smart homes using image processing and Machine Learning techniques. FireD extracts the features from photos and captured video frames using Convolutional Neural Network (CNN) and in turn sends them to Neural Network which implements clustering algorithm known as Yolov5 to ensure the ability to classify images as Fire and Non-Fire. Once the fire is detected, model will send the images to Heroku cloud which serves as container based cloud Platform as a Service (PaaS) to access, deploy and manage the images. On the detection of fire Notification is sent to Telegram through telegram bot. Overall performance data from model indicates that FireD is likely to perform well in real-world scenarios. Therefore, FireD is more reliable than other existing systems since FireD application is pushed to the docker container with all the required libraries and files. The application can be accessed and implemented easily. © 2024 IEEE.

关键词： Platform as a Service (PaaS)

来源：评论

学校读者我要写书评

暂无评论

TinyLUT: Tiny Look-Up Table for Efficient image Restoration at the Edge 38

TinyLUT: Tiny Look-Up Table for Efficient Image Restoration ...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Li, Huanan Guan, Juntao Lai, Rui Ma, Sijun Gu, Lin Zhu, Zhangming China School of Integrated Circuits Xidian University Xi'an China Hangzhou Institute of Technology Xidian University Hangzhou China RIKEN AIP Tokyo103-0027 Japan The University of Tokyo Japan

Look-up tables(LUTs)-based methods have recently shown enormous potential in image restoration tasks, which are capable of significantly accelerating the inference. However, the size of LUT exhibits exponential growth with the convolution kernel size, creating a storage bottleneck for its broader application on edge devices. Here, we address the storage explosion challenge to promote the capacity of mapping the complex CNN models by LUT. We introduce an innovative separable mapping strategy to achieve over 7× storage reduction, transforming the storage from exponential dependence on kernel size to a linear relationship. Moreover, we design a dynamic discretization mechanism to decompose the activation and compress the quantization scale that further shrinks the LUT storage by 4.48×. As a result, the storage requirement of our proposed TinyLUT is around 4.1% of MuLUT-SDY-X2 and amenable to on-chip cache, yielding competitive accuracy with over 5× lower inference latency on Raspberry 4B than FSRCNN. Our proposed TinyLUT enables superior inference speed on edge devices with new state-of-the-art accuracy on both of image super-resolution and denoising, showcasing the potential of applying this method to various image restoration tasks at the edge. The codes are available at: https://***/Jonas-KD/TinyLUT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on algorithms of Computer image Intelligent Recognition and Deep Learning 2

Research on Algorithms of Computer Image Intelligent Recogni...

引用

2nd International conference on Signal image processing and Communication, ICSIPC 2022

作者： Shao, Zheneenji Zhou, Jingxuan Sichuan University Chengdu China Dalian University of Technology Dalian China

ISBN: (纸本)9781510657694

In recent years, with the rapid development of science and technology in my country, people's requirements for computer information technology have become higher and higher. In order to better explore new things, engineers and technicians need to continuously optimize computer information processing systems to help people better solve practical problems. The article mainly analyzes the development process of computer intelligent image recognition algorithms, expounds the computer intelligent image recognition algorithm, and finally puts forward the technical application of computer intelligent image recognition algorithm, which provides a certain research foundation for related staff. © 2022 SPIE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Thorax Disease Classification Based on the Convolutional Network SqueezeNet 12

Thorax Disease Classification Based on the Convolutional Net...

引用

12th IEEE International conference on Intelligent Data Acquisition and Advanced Computing systems: Technology and Applications, IDAACS 2023

作者： Avanzato, Roberta Beritelli, Francesco University of Catania Dieei Catania95125 Italy

ISBN: (纸本)9798350358056

Chest radiography allows a detailed inspection of a patient's thorax via an imaging modality, but requires specialized training for proper interpretation. With the advent of high performance general purpose image analysis and computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. In this paper, we propose a classification algorithm distinguishing between chest radiographs performed on people with or without lung disease. The dataset used as the input to the SqueezeNet neural network is Chest X-ray. The only pre-processing phase applied to the dataset is the resize to 224×224 and the conversion to grayscale. The accuracy percentage obtained during the network testing phase is 94%. © 2023 IEEE.

关键词： computer vision Convolutional neural network deep learning healthcare image processing

来源：评论

学校读者我要写书评

暂无评论

image Interpolation with Edges Preserving and Implementation on the Real ADAS Platform 5

Image Interpolation with Edges Preserving and Implementation...

引用

5th IEEE International conference on image processing Applications and systems (IPAS)

作者： Kelava, Bozidar Vranjes, Mario Vranjes, Denis Lukac, Zeljko TTTechAuto CEE Osijek Croatia Fac Elect Engn Comp Sci & Informat Technol Osijek Croatia Fac Tech Sci Novi Sad Serbia

ISBN: (纸本)9781665462198

To save transmission, processing and memory resources in Advanced Driver Assistance systems (ADAS), it is often necessary to reduce the image resolution. Sometimes it is necessary to increase it after the transmission. Both resolution changes involve an image interpolation process. This paper describes implementation for three well-known interpolation methods, nearest neighbour interpolation (NN), bilinear interpolation (BL) and bicubic interpolation (BC), on a real automotive AMV ALPHA platform, using multiple processors on the same System on Chip (SoC). Implementation was done using C programming language and Vision Software Development Kit (VSDK). Specific attention is given to the optimal distribution of tasks to the certain processor. The results have shown that, on the real automotive AMV ALPHA platform, BL interpolation achieves the best trade-off between the quality of interpolated image for the usage in automotive image-processing based algorithms and execution time, especially for the algorithms where the lower frame rate is acceptable (like surround-view, park assist, etc.).

关键词： image interpolation ADAS real-time

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based image processing for Defect Detection in Electronic Components Manufacturing

Deep Learning-Based Image Processing for Defect Detection in...

引用

2024 International conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2024

作者： Mathivanan, B. Maruthupandi, J. Lakshmi, Namala Vijaya Suvitha, S. Karthik, K. Swaroop, Anand Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore641022 India New Horizon College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru560103 India Kkr & Ksr Institute of Technology and Sciences Department of Computer Science and Engineering Andhra Pradesh 522017 India S.A. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai600077 India Velammal College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Madurai625009 India Institute of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Lucknow226021 India

ISBN: (纸本)9798331543617

In electronic factors manufacturing, icing product quality through disfigurement discovery is pivotal for maintaining trustability and performance norms. This exploration investigates the operation of deep literacy ways in image processing for disfigurement discovery. Deep literacy algorithms, particularly convolutional neural networks(CNNs), have shown remarkable success in automated image analysis tasks. This study explores their effectiveness in relating blights similar to face abnormalities, cracks, or indecorous assembly in electronic factors. By using annotated datasets and advanced neural network infrastructures, the proposed approach aims to enhance delicacy and effectiveness in disfigurement discovery compared to traditional styles. The methodology involves preprocessing raw images, training CNN models on labeled data, and validating their performance through rigorous testing and evaluation. Results demonstrate the eventuality of deep literacy to revise disfigurement discovery processes in manufacturing, offering more dependable examinations that contribute to bettered product quality and reduced product costs. This exploration contributes precious perceptivity to the integration of AI technologies for enhancing quality control in artificial settings. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of A Multi-Core CPU Compilation Optimization Framework Based on MLIR 3

Design and Implementation of A Multi-Core CPU Compilation Op...

引用

3rd International conference on Electronic Information Engineering and Computer Communication, EIECC 2023

作者： Gao, Han Zhao, Yixuan Yan, Tanbao Zhao, Yuhong Aeronautics Computing Technology Research Institute Xi'an China

ISBN: (纸本)9798350359961

Most on-board software is developed and adapted around traditional hardware resources. When high-performance hardware is introduced to the on-board heterogeneous computing platform, on-board software cannot fully leverage the processing capabilities of the high-performance hardware, making it difficult to meet the real-Time requirements of multiple application tasks. For signal processing algorithms and other non-matrix complex scientific computing tasks to be arranged and adapted on multi-core CPUs, traditional algorithms are mainly developed based on DSP processors, making it difficult to directly deploy them on multi-core CPU processors. This article proposes and constructs a MLIR-based multi-core CPU compilation optimization framework, designs an automatic software code execution optimization process, achieves full adaptation of on-board software on multi-core CPU resources, improves the processing efficiency of complex scientific computing tasks, and solves the problem of poor real-Time performance of complex scientific computing tasks. Compared with the two types of compilation optimization systems currently in use, the average speedup ratio was 7.54 and 3.26 times, respectively. © 2023 IEEE.

关键词： Compilation optimization MLIR multicore CPU parallelism

来源：评论

学校读者我要写书评

暂无评论

image Classifications Methods Analysis with Differen Methods to for Identifying best image Layout with High Resolution

Image Classifications Methods Analysis with Differen Methods...

引用

2023 International conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Mahesh, T.R. Vivek, V. Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350322309

This researcher investigated effective much eye opening and pattern detection algorithms. Finally, this article used two frameworks to argue that geospatial investigation systems for patterns are necessary. One of most popular method for analyzing photographs using image processing and analysis math is probably visual configuration methods. imagery description is also necessary for the evaluation of remote sensing tools used for thorough land investigation. The three main image configuration techniques that are often used for far detection are opinion piece visual analysis, controlled groupings, and solos visual categorization. The approach used in these image layout techniques is combined in the present study. The present study also briefly summarizes each approach's use in exploring distant sensing info while also outlining the steps for each way using stream outlines and frameworks. Generally speaking, a quick overview of image layout techniques is included in the test. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

A Lightweight image Encryption Algorithm Based on Double Chaotic systems and DNA Encoding 2

A Lightweight Image Encryption Algorithm Based on Double Cha...

引用

2nd International conference on Frontiers of Communications, Information System and Data Science, CISDS 2023

作者： You, Li Yang, Tian-Yu Jin, Zhe-Xue Yanbian University Department of Computer Science and Technology Jilin Yanji China College of Mechanical and Electrical Engineering Hebei Agricultural University Hebei Baoding China

ISBN: (纸本)9798350381474

In the age of big data, many fields generate massive images every day. In order to protect the privacy of image data, image encryption is often used to prevent privacy leakage. However, most of the current encryption algorithms ignore the overall operation efficiency of the algorithm in order to ensure better encryption effect. Moreover, encrypting images requires a lot of computing resources, which cannot meet most practical application scenarios. In order to ensure the security performance of the encryption algorithm and improve the encryption speed. In this paper, a lightweight image encryption algorithm based on the combination of double chaotic system and DNA coding is proposed. In order to ensure the security of the algorithm, logistic chaos and PWLCM chaos are used as the double chaotic systems that generate key sequences, and DNA coding calculations are integrated to improve the complexity of the algorithm. In order to balance the complexity of the algorithm and the computational overhead, to achieve the lightweight calculation of the encryption algorithm. After the image bit plane decomposition, only the upper four-bit binary sequence, which contains most of the image information, is diffused. This ensures that most of the information in the image is changed while reducing the computational overhead by half. Simulation results show that the encryption algorithm not only consumes low computing resources, but also obtains good encryption effect with only one round of encryption, which is suitable for batch image encryption tasks. © 2023 IEEE.

关键词： Chaotic systems

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：