• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

大数据下软压缩图像编码算法的健壮性、实用性和全面性分析。

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data.

机构信息

The Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China.

The Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China.

出版信息

Sci Rep. 2023 Feb 2;13(1):1958. doi: 10.1038/s41598-023-29068-z.

DOI:10.1038/s41598-023-29068-z
PMID:36732352
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9895050/
Abstract

With the advancement of intelligent vision algorithms and devices, image reprocessing and secondary propagation are becoming increasingly prevalent. A large number of similar images are being produced rapidly and widely, resulting in the homogeneity and similarity of images. Moreover, it brings new challenges to compression systems, which need to exploit the potential of deep features and side information of images. However, traditional methods are incompetent for this issue. Soft compression is a novel data-driven image coding algorithm with superior performance. Compared with existing paradigms, it has distinctive characteristics: from hard to soft, from pixels to shapes, and from fixed to random. Soft compression may hold promise for human-centric/data-centric intelligent systems, making them efficient and reliable and finding potential in the metaverse and digital twins, etc. In this paper, we present a comprehensive and practical analysis of soft compression, revealing the functional role of each component in the system.

摘要

随着智能视觉算法和设备的进步，图像的再处理和二次传播变得越来越普遍。大量相似的图像正在迅速广泛地生成，导致图像的同质性和相似性增加。此外，这给压缩系统带来了新的挑战，需要利用图像的深度特征和辅助信息的潜力。然而，传统方法对此问题无能为力。软压缩是一种新颖的数据驱动的图像编码算法，具有优异的性能。与现有范例相比，它具有独特的特点：从硬到软，从像素到形状，从固定到随机。软压缩可能对以人为中心/以数据为中心的智能系统有帮助，使它们高效可靠，并在元宇宙和数字孪生等领域中发现潜力。在本文中，我们对软压缩进行了全面而实用的分析，揭示了系统中每个组件的功能作用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/638fc9a78821/41598_2023_29068_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/ef3f195aea57/41598_2023_29068_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/de9e673ec52d/41598_2023_29068_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/d473c587953a/41598_2023_29068_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/adf6740adf89/41598_2023_29068_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/097bce9db520/41598_2023_29068_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/b600cecba386/41598_2023_29068_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/38c2fb86bd67/41598_2023_29068_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/e77154b4badf/41598_2023_29068_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/638fc9a78821/41598_2023_29068_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/ef3f195aea57/41598_2023_29068_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/de9e673ec52d/41598_2023_29068_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/d473c587953a/41598_2023_29068_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/adf6740adf89/41598_2023_29068_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/097bce9db520/41598_2023_29068_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/b600cecba386/41598_2023_29068_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/38c2fb86bd67/41598_2023_29068_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/e77154b4badf/41598_2023_29068_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2c76/9895050/638fc9a78821/41598_2023_29068_Fig9_HTML.jpg

相似文献

1
Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data.大数据下软压缩图像编码算法的健壮性、实用性和全面性分析。
Sci Rep. 2023 Feb 2;13(1):1958. doi: 10.1038/s41598-023-29068-z.
2
Soft Compression for Lossless Image Coding Based on Shape Recognition.基于形状识别的无损图像编码软压缩
Entropy (Basel). 2021 Dec 14;23(12):1680. doi: 10.3390/e23121680.
3
Region of interest extraction for lossless compression of bone X-ray images.用于骨X光图像无损压缩的感兴趣区域提取
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:3061-4. doi: 10.1109/EMBC.2015.7319038.
4
Region-based wavelet coding methods for digital mammography.用于数字乳腺摄影的基于区域的小波编码方法。
IEEE Trans Med Imaging. 2003 Oct;22(10):1288-96. doi: 10.1109/TMI.2003.817812.
5
A Novel Light Field Image Compression Method Using EPI Restoration Neural Network.基于 EPI 恢复神经网络的新型光场图像压缩方法。
Biomed Res Int. 2022 Jun 13;2022:8324438. doi: 10.1155/2022/8324438. eCollection 2022.
6
Why Shape Coding? Asymptotic Analysis of the Entropy Rate for Digital Images.为什么是形状编码？数字图像熵率的渐近分析。
Entropy (Basel). 2022 Dec 27;25(1):48. doi: 10.3390/e25010048.
7
Performance analysis of reversible image compression techniques for high-resolution digital teleradiology.高分辨率数字远程放射学中可逆图像压缩技术的性能分析。
IEEE Trans Med Imaging. 1992;11(3):430-45. doi: 10.1109/42.158947.
8
[The compression of numerical radiological images].[数字放射图像的压缩]
Radiol Med. 1994 Nov;88(5):631-42.
9
Cloud solution for histopathological image analysis using region of interest based compression.基于感兴趣区域压缩的组织病理学图像分析云解决方案。
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:1202-1205. doi: 10.1109/EMBC.2017.8037046.
10
Lossless image compression with multiscale segmentation.基于多尺度分割的无损图像压缩。
IEEE Trans Image Process. 2002;11(11):1228-37. doi: 10.1109/TIP.2002.804528.

本文引用的文献

1
Why Shape Coding? Asymptotic Analysis of the Entropy Rate for Digital Images.为什么是形状编码？数字图像熵率的渐近分析。
Entropy (Basel). 2022 Dec 27;25(1):48. doi: 10.3390/e25010048.
2
EXK-SC: A Semantic Communication Model Based on Information Framework Expansion and Knowledge Collision.EXK-SC：一种基于信息框架扩展和知识碰撞的语义通信模型。
Entropy (Basel). 2022 Dec 17;24(12):1842. doi: 10.3390/e24121842.
3
Soft Compression for Lossless Image Coding Based on Shape Recognition.基于形状识别的无损图像编码软压缩
Entropy (Basel). 2021 Dec 14;23(12):1680. doi: 10.3390/e23121680.
4
A lossless compression method for multi-component medical images based on big data mining.基于大数据挖掘的多分量医学图像无损压缩方法。
Sci Rep. 2021 Jun 11;11(1):12372. doi: 10.1038/s41598-021-91920-x.
5
Attention to the Variation of Probabilistic Events: Information Processing with Message Importance Measure.关注概率事件的变化：基于消息重要性度量的信息处理
Entropy (Basel). 2019 Apr 26;21(5):439. doi: 10.3390/e21050439.
6
Image Coding with Data-Driven Transforms: Methodology, Performance and Potential.基于数据驱动变换的图像编码：方法、性能与潜力
IEEE Trans Image Process. 2020 Sep 24;PP. doi: 10.1109/TIP.2020.3025203.
7
Image quality assessment: from error visibility to structural similarity.图像质量评估：从误差可见性到结构相似性。
IEEE Trans Image Process. 2004 Apr;13(4):600-12. doi: 10.1109/tip.2003.819861.