检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Ruan, Cihan Yang, Liang Han, Rongduo Gao, Shan Wu, Haoyu Ling, Nam Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA Nankai Univ Coll Software Tianjin Peoples R China Nankai Univ Sch Math Sci Tianjin Peoples R China Nankai Univ Coll Life Sci Tianjin Peoples R China Roku Inc San Jose CA USA

ISBN: (纸本)9798350330991;9798350331004

DNA storage is a promising data storage method with high density, durability, and easy maintenance, ideal for data archiving. However, wide-scale adoption is hindered by challenges like high synthesis costs, data loss, and I/O complexities. Addressing robustness is a primary concern in advancing DNA storage. Traditional strategies for robustness rely on increasing redundancy, replicas, and error-correction codes (ECC) for each DNA sequence strand. Given the unpredictable errors in DNA storage and the associated costs of absolute accuracy, we've embraced an error-tolerance approach. This paper introduces an innovative method utilizing the residual Convolutional Neural Network (CNN) during image decoding in DNA storage to combat noise and enhance robustness. We simulated compressed images in DNA sequences and restored them using our network, achieving commendable peak signal-to-noise ratios (PSNR) even with lower-quality images. Our method offers a balance between redundancy and image quality in DNA storage.

关键词： DNA storage Error tolerance Robustness image decoding Residual learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating Deep Learning Tasks with Optimized GPU-assisted image decoding 26

Accelerating Deep Learning Tasks with Optimized GPU-assisted...

引用

26th IEEE International Conference on Parallel and Distributed Systems (IEEE ICPADS)

作者： Wang, Lipeng Luo, Qiong Yan, Shengen HKUST Dept Comp Sci & Engn Hong Kong Peoples R China SenseTime Res Shenzhen Peoples R China

ISBN: (纸本)9781728190747

In computer vision deep learning (DL) tasks, most of the input image datasets are stored in the JPEG format. These JPEG datasets need to be decoded before DL tasks are performed on them. We observe two problems in the current JPEG decoding procedures for DL tasks: (1) the decoding of image entropy data in the decoder is performed sequentially, and this sequential decoding repeats with the DL iterations, which takes significant time;(2) Current parallel decoding methods under-utilize the massive hardware threads on GPUs. To reduce the image decoding time, we introduce a pre-scan mechanism to avoid the repeated image scanning in DL tasks. Our pre-scan generates boundary markers for entropy data so that the decoding can be performed in parallel. To cooperate with the existing dataset storage and caching, systems, we propose two modes of the pre-scan mechanism: a compatible mode and a fist mode. The compatible mode does not change the image file structure so pre-scanned files can be stored back to disk for subsequent DL tasks. In comparison, the fast mode crafts a JPEG image into a binary format suitable for parallel decoding, which can be processed directly on the GPU. Since the GPU has thousands of hardware threads, we propose a fine-grained parallel decoding method on the pre-scanned dataset. The fine-grained parallelism utilizes the GPU effectively, and achieves speedups of around 1.5x over existing GPU-assisted image decoding libraries on real-world DL tasks.

关键词： deep learning image decoding parallel processing heterogeneous processing GPU

来源：评论

学校读者我要写书评

暂无评论

An Experimental Analysis of Predictive Coding Based On Artificial Neural Networks for image decoding

An Experimental Analysis of Predictive Coding Based On Artif...

引用

作者： Sun, Yanbo PennState University Libraries

学位级别：Master of Science

Prediction techniques have been extensively studied for images and video compression over the last few decades. Currently, most existing images and video compression solutions contain some predictive encoding in their algorithms. For example, it is well known that the 25-year history of the joint image group (JPEG) image coding standard predictive encodes quantified DC transform coefficients. There some other sorts of predictive coding techniques which implement redundancies inside images and videos. Similarly, in some particular cases such as image sequences, the compression system usually uses the motion compensation prediction to utilize the time redundancy. We discuss some of the most essential predictive coding techniques used in state-of-the-art image and video encoders. Then we provide some basic concepts about video color spaces representation. Various technologies including linear and non-linear predictions methods are presented in the following *** this thesis, we have implemented and presented an Artificial Neural Network Approach for the encoding of JPEG images. We have shown that JPEG compression can be significantly improved with our decoding method. In these experiments, we have implemented MLP and RNN models on tiny-imagenet data sets. We performed stateless and stateful prediction without using spatial information as well as predictions using partial spatial information and full spatial information. We use the partial and full spatial redundancy in the image to implement a nonlinear mapping function. Compared with the original image, the proposed method outperforms the JPEG image in generating predictive images with relatively small distortion.

关键词： Artificial Neural Network image decoding Predictive Coding Spatial Redundancies

来源：评论

学校读者我要写书评

暂无评论

FD-CNN: A Frequency-Domain FPGA Acceleration Scheme for CNN-Based image-Processing Applications

引用

ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS 2023年第6期22卷 1-30页

作者： Wang, Xiaoyang Zhou, Zhe Yuan, Zhihang Zhu, Jingchen Cao, Yulong Zhang, Yao Sun, Kangrui Sun, Guangyu Peking Univ Sch Comp Sci Beijing Peoples R China Peking Univ Sch Integrated Circuits Beijing Peoples R China Adv Inst Informat Technol AIIT Hangzhou Peoples R China

In the emerging edge-computing scenarios, FPGAs have been widely adopted to accelerate convolutional neural network (CNN)-based image-processing applications, such as image classification, object detection, and image segmentation, and so on. A standard image-processing pipeline first decodes the collected compressed images from Internet of Things (IoTs) to RGB data, then feeds them into CNN engines to compute the results. Previous works mainly focus on optimizing the CNN inference parts. However, we notice that on the popular ZYNQ FPGA platforms, image decoding can also become the bottleneck due to the poor performance of embedded ARM CPUs. Even with a hardware accelerator, the decoding operations still incur considerable latency. Moreover, conventional RGB-based CNNs have too few input channels at the first layer, which can hardly utilize the high parallelism of CNN engines and greatly slows down the network inference. To overcome these problems, in this article, we propose FD-CNN, a novel CNN accelerator leveraging the partial-decoding technique to accelerate CNNs directly in the frequency domain. Specifically, we omit the most time-consuming IDCT (Inverse Discrete Cosine Transform) operations of image decoding and directly feed the DCT coefficients (i.e., the frequency data) into CNNs. By this means, the image decoder can be greatly simplified. Moreover, compared to the RGB data, frequency data has a narrower input resolution but has 64x more channels. Such an input shape is more hardware friendly than RGB data and can substantially reduce the CNN inference time. We then systematically discuss the algorithm, architecture, and command set design of FD-CNN. To deal with the irregularity of different CNN applications, we propose an image-decoding-aware design-space exploration (DSE) workflow to optimize the pipeline. We further propose an early stopping strategy to tackle the time-consuming progressive JPEG decoding. Comprehensive experiments demonstrate that FD-CNN

关键词： Edge computing image decoding Convolutional Neural Network FPGA

来源：评论

学校读者我要写书评

暂无评论

DIESEL plus : Accelerating Distributed Deep Learning Tasks on image Datasets

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2022年第5期33卷 1173-1184页

作者： Wang, Lipeng Luo, Qiong Yan, Shengen Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China SenseTime Res Shenzhen 518000 Guangdong Peoples R China

We observe that data access and processing takes a significant amount of time in large-scale deep learning training tasks (DLTs) on image datasets. Three factors contribute to this problem: (1) the massive and recurrent accesses to large numbers of small files;(2) the repeated, expensive decoding computation on each image, and (3) the frequent communication between computation nodes and storage nodes. Existing work has addressed some aspects of these problems;however, no end-to-end solutions have been proposed. In this article, we propose DIESEL+, an all-in-one system which accelerates the entire I/O pipeline of deep learning training tasks. DIESEL+ contains several components: (1) local metadata snapshot;(2) per-task distributed caching;(3) chunk-wise shuffling;(4) GPU-assisted image decoding and (5) online region-of-interest (ROI) decoding. The metadata snapshot removes the bottleneck on metadata access in frequent reading of large numbers of files. The per-task distributed cache across the worker nodes of a DLT task to reduce the I/O pressure on the underlying storage. The chunk-based shuffle method converts small file reads into large chunk reads, so that the performance is improved without sacrificing the training accuracy. The GPU-assisted image decoding and the online ROI method minimize the image decoding workloads and reduce the cost of data movement between nodes. These techniques are seamlessly integrated into the system. In our experiments, DIESEL+ outperforms existing systems by a factor of two to three times on the overall training time.

关键词： decoding Training Task analysis Transform coding Deep learning Metadata image coding Storage system dataset management deep learning distributed cache dataset shuffling image decoding GPU

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Multispectral images Color Contrast Processing Obtained from Spacecraft or Unmanned Aerial Vehicle 2

An Improved Method for Multispectral Images Color Contrast P...

引用

IEEE 2nd Ukrainian Microwave Week (UkrMW)

作者： Nekhin, Mariia Hordiichuk, Valerii Perehuda, Oleksandr Frolov, Serhii Natl Space Facil Control & Test Ctr Earth Remote Sensing Data Proc Grp Zhitomir Ukraine Natl Def Univ Ukraine Ctr Mil & Strateg Studies Kiev Ukraine Korolyov Zhytomyr Mil Inst Sci Ctr Zhitomir Ukraine Natl Def Univ Ukraine Dept Naval Forces Kiev Ukraine

ISBN: (纸本)9798350331523

The work substantiates the expediency of developing methods for thematic processing of multispectral images obtained from space or unmanned aerial vehicles. A method of a color combination selecting in the channels of the processed image for the synthesis of an image with false colors is proposed. This approach based on the combined using of: color contrast method (the method of false colors) as it is, the commercial software "ENVI" and the developed software "Deciphering Atlas". The methodology involves the construction of a deciphering atlas for a specific sensor, installed on spacecraft or unmanned aerial vehicle. The proposed approach makes it possible to speed up the processing of multispectral images.

关键词： multispectral image remote sensing image decoding spacecraft unmanned aerial vehicle

来源：评论

学校读者我要写书评

暂无评论

An Optical Multiplexing Method Using Upconversion Nanoparticles with Tunable P-I Relationship

引用

ADVANCED OPTICAL MATERIALS 2022年第22期10卷

作者： Chen, Xinyu Gu, Yuyang Chai, Yingjie Wu, Na Wen, Chenqing Ke, Jiaming Sun, Yishuo Li, Fuyou Feng, Wei Fudan Univ Dept Chem Shanghai 200433 Peoples R China Fudan Univ State Key Lab Mol Engn Polymers Shanghai 200433 Peoples R China

Optical multiplexing is of great value in information acquisition due to its excellent signal encoding ability. However, the number of encoding channels is often limited by instruments or luminescent materials used as information carriers in practical applications. To provide a new option, an optical multiplexing method based on the tunable relationship between excitation power density and emission intensity of upconversion nanoparticles (UCNPs;P-I relationship), which can be regulated by the co-doping ratio of sensitizer ions and activator ions, is developed. This method can be implemented on commonly used optical imaging equipment. Since the P-I relationship is only related to the energy transfer process of lanthanide ions in UCNPs, it has the potential to be combined with other dimensions of optical multiplexing such as wavelength and intensity to provide more robust encoding ability.

关键词： image decoding lanthanide nanomaterials optical multiplexing power dependence upconversion

来源：评论

学校读者我要写书评

暂无评论

A Lossless image Compression Algorithm Based On Group Encoding 10

A Lossless Image Compression Algorithm Based On Group Encodi...

引用

10th International Conference on Advanced Computer Information Technologies (ACIT)

作者： Koval, Vasyl Yatskiv, Vasyl Yakymenko, Igor Zahorodnia, Diana Ternopil Natl Econ Univ Dept Informat Comp Syst & Control 8 Chekhova Str Ternopol Ukraine Ternopil Natl Econ Univ Dept Cyber Secur 8 Chekhova Str Ternopol Ukraine

ISBN: (纸本)9781728167602

This paper considers a new lossless image compression algorithm that provides reduction of data redundancy in video processing systems. To achieve the high compression level group encoding approach is proposed. The experimental research shows that proposed algorithm provides 1.33 times better compression quality index than the Run Length Encoding (RLE) algorithm.

关键词： image encoding image decoding image compression group encoding lossless compression Run Length Encoding (RLE) data compression

来源：评论

学校读者我要写书评

暂无评论

Intelligent Detection Platform for Simultaneous Detection of Multiple MiRNAs Based on Smartphone

引用

ACS SENSORS 2019年第7期4卷 1873-1880页

作者： Tian, Yu Zhang, Lili Wang, Hanjie Ji, Wanying Zhang, Ziyu Zhang, Yingying Yang, Zhengchun Cao, Zongsheng Zhang, Shufang Chang, Jin Tianjin Univ Sch Life Sci 92 Weijin Rd Tianjin 300072 Peoples R China Tianjin Univ Sch Elect & Informat Engn 92 Weijin Rd Tianjin 300072 Peoples R China Tianjin Univ Tianjin Int Engn Inst 92 Weijin Rd Tianjin 300072 Peoples R China Tianjin Univ Technol Tianjin Key Lab Film Elect & Commun Devices Sch Elect & Elect Engn Tianjin 300384 Peoples R China

As a marker of malignant tumors, miRNA is closely related to the occurrence and metastasis of tumors. How to achieve rapid and sensitive real-time detection is important for clinical prevention and treatment of cancer. In this study, an intelligent detection platform based on smartphone image processing technology made point-of-care testing a reality. This new smart approach could detect multiple targets simultaneously and sensitively. Hydrogel microparticles of different coding modes (shapes, numbers) were prepared by flow lithography to detect different miRNAs. After sandwich immunoassays, different shapes of hydrogels showed different fluorescence intensities depending on their targets. images were captured by a smartphone and then analyzed by image recognition processing software installed on the smartphone. The concentration of miRNA was obtained within 10 s. The entire reaction process did not exceed 2 h. This intelligent and portable detection platform for miRNAs was reliable and the limit of detection reached the femtomole level. This work provided a demonstration of intelligent, portable, real-time detection of tumor markers.

关键词： smartphone app image decoding miRNA detection polymer microparticles point-of-care testing

来源：评论

学校读者我要写书评

暂无评论

An Effective Data Hiding Mechanism Based on Encrypted images

An Effective Data Hiding Mechanism Based on Encrypted Images

引用

Innovative Trends and Advances in Engineering and Technology (ICITAET), International Conference on

作者： Aniket K. Shahade Priyanka V. Deshmukh A. S. Kapse V. M. Thakare SSGMCE Shegaon AEC Chikhali Dept. of CSE SGBAU Amravati

ISBN: (数字)9781728119014

ISBN: (纸本)9781728119021

Now a day's to stay up secrecy associated confidentiality of an data can be a vibrant field with two completely different approaches being followed, the first being encrypting the images through cryptography algorithms victimization keys, the other approach involves concealing information victimization information concealing algorithmic rule to stay up the images secrecy. A content owner use cryptography key to perform the cryptography of original footage, and using a data concealing key an information hider can plant any data into the encrypted image though he does not acknowledge the primary content, as a result of the encrypted image contains some any data, with the help of cryptography key a receiver first decipher it then extract the embedded data and recover the primary image in line with the data-hiding key.

关键词： Cowl image Knowledge concealing Knowledge extraction image secret writing image decoding Knowledge recovery DWT Information Extraction cryptography images Hidden data Privacy Victimization Confidentiality imagery (Psychotherapy) image

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：