• 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

基于改进权重函数的多曝光图像融合算法

Multi-Exposure Image Fusion Algorithm Based on Improved Weight Function.

作者信息

Xu Ke, Wang Qin, Xiao Huangqing, Liu Kelin

机构信息

College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China.

出版信息

Front Neurorobot. 2022 Mar 8;16:846580. doi: 10.3389/fnbot.2022.846580. eCollection 2022.

DOI:10.3389/fnbot.2022.846580
PMID:35345477
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8957254/
Abstract

High-dynamic-range (HDR) image has a wide range of applications, but its access is limited. Multi-exposure image fusion techniques have been widely concerned because they can obtain images similar to HDR images. In order to solve the detail loss of multi-exposure image fusion (MEF) in image reconstruction process, exposure moderate evaluation and relative brightness are used as joint weight functions. On the basis of the existing Laplacian pyramid fusion algorithm, the improved weight function can capture the more accurate image details, thereby making the fused image more detailed. In 20 sets of multi-exposure image sequences, six multi-exposure image fusion methods are compared in both subjective and objective aspects. Both qualitative and quantitative performance analysis of experimental results confirm that the proposed multi-scale decomposition image fusion method can produce high-quality HDR images.

摘要

高动态范围（HDR）图像有广泛的应用，但对其访问有限。多曝光图像融合技术因其能获得类似于HDR图像的图像而受到广泛关注。为了解决多曝光图像融合（MEF）在图像重建过程中的细节损失问题，将曝光适度评估和相对亮度用作联合权重函数。在现有的拉普拉斯金字塔融合算法基础上，改进后的权重函数能够捕捉到更精确的图像细节，从而使融合后的图像更加详细。在20组多曝光图像序列中，从主观和客观两个方面对六种多曝光图像融合方法进行了比较。实验结果的定性和定量性能分析均证实，所提出的多尺度分解图像融合方法能够生成高质量的HDR图像。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/71d264c3d245/fnbot-16-846580-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/98f465af4f47/fnbot-16-846580-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/f60f7d3ad55a/fnbot-16-846580-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/55cbb43a12d8/fnbot-16-846580-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/dac375c9a49e/fnbot-16-846580-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/1767ee283ac3/fnbot-16-846580-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/311cc1b741c0/fnbot-16-846580-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/71d264c3d245/fnbot-16-846580-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/98f465af4f47/fnbot-16-846580-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/f60f7d3ad55a/fnbot-16-846580-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/55cbb43a12d8/fnbot-16-846580-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/dac375c9a49e/fnbot-16-846580-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/1767ee283ac3/fnbot-16-846580-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/311cc1b741c0/fnbot-16-846580-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/241e/8957254/71d264c3d245/fnbot-16-846580-g0007.jpg

相似文献

1
Multi-Exposure Image Fusion Algorithm Based on Improved Weight Function.基于改进权重函数的多曝光图像融合算法
Front Neurorobot. 2022 Mar 8;16:846580. doi: 10.3389/fnbot.2022.846580. eCollection 2022.
2
A Novel Multi-Exposure Image Fusion Method Based on Adaptive Patch Structure.一种基于自适应块结构的新型多曝光图像融合方法
Entropy (Basel). 2018 Dec 6;20(12):935. doi: 10.3390/e20120935.
3
A sum-modified-Laplacian and sparse representation based multimodal medical image fusion in Laplacian pyramid domain.基于拉普拉斯金字塔域中和的拉普拉斯算子和稀疏表示的多模态医学图像融合。
Med Biol Eng Comput. 2019 Oct;57(10):2265-2275. doi: 10.1007/s11517-019-02023-9. Epub 2019 Aug 14.
4
A Precise Multi-Exposure Image Fusion Method Based on Low-level Features.一种基于底层特征的精确多曝光图像融合方法。
Sensors (Basel). 2020 Mar 13;20(6):1597. doi: 10.3390/s20061597.
5
Detail-Enhanced Multi-Scale Exposure Fusion.细节增强多尺度曝光融合。
IEEE Trans Image Process. 2017 Mar;26(3):1243-1252. doi: 10.1109/TIP.2017.2651366. Epub 2017 Jan 16.
6
Multimodal medical image fusion via laplacian pyramid and convolutional neural network reconstruction with local gradient energy strategy.基于拉普拉斯金字塔和卷积神经网络重建并采用局部梯度能量策略的多模态医学图像融合
Comput Biol Med. 2020 Nov;126:104048. doi: 10.1016/j.compbiomed.2020.104048. Epub 2020 Oct 8.
7
Multi-modal medical image fusion by Laplacian pyramid and adaptive sparse representation.基于拉普拉斯金字塔和自适应稀疏表示的多模态医学图像融合
Comput Biol Med. 2020 Aug;123:103823. doi: 10.1016/j.compbiomed.2020.103823. Epub 2020 Jun 20.
8
Multi-exposure electric power monitoring image fusion method without ghosting based on exposure fusion framework and color dissimilarity feature.基于曝光融合框架和颜色差异特征的无重影多曝光电力监测图像融合方法
Front Neurorobot. 2023 Jan 10;16:1105385. doi: 10.3389/fnbot.2022.1105385. eCollection 2022.
9
Perceptual Evaluation for Multi-Exposure Image Fusion of Dynamic Scenes.动态场景多曝光图像融合的感知评价
IEEE Trans Image Process. 2019 Sep 16. doi: 10.1109/TIP.2019.2940678.
10
Multi-exposure X-ray image fusion quality evaluation based on CSF and gradient amplitude similarity.基于对比度敏感函数（CSF）和梯度幅度相似性的多曝光X射线图像融合质量评估
J Xray Sci Technol. 2021;29(4):697-709. doi: 10.3233/XST-210871.

引用本文的文献

1
Endoscopic Image Enhancement: Wavelet Transform and Guided Filter Decomposition-Based Fusion Approach.内镜图像增强：基于小波变换和引导滤波分解的融合方法。
J Imaging. 2024 Jan 20;10(1):28. doi: 10.3390/jimaging10010028.

本文引用的文献

1
How to Analyze the Neurodynamic Characteristics of Pulse-Coupled Neural Networks? A Theoretical Analysis and Case Study of Intersecting Cortical Model.如何分析脉冲耦合神经网络的神经动力学特性？交叉皮质模型的理论分析与案例研究
IEEE Trans Cybern. 2022 Jul;52(7):6354-6368. doi: 10.1109/TCYB.2020.3043233. Epub 2022 Jul 4.
2
Fast Multi-Scale Structural Patch Decomposition for Multi-Exposure Image Fusion.用于多曝光图像融合的快速多尺度结构补丁分解
IEEE Trans Image Process. 2020 Apr 16. doi: 10.1109/TIP.2020.2987133.
3
A Precise Multi-Exposure Image Fusion Method Based on Low-level Features.
一种基于底层特征的精确多曝光图像融合方法。
Sensors (Basel). 2020 Mar 13;20(6):1597. doi: 10.3390/s20061597.
4
Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach.鲁棒多曝光图像融合：一种结构补丁分解方法。
IEEE Trans Image Process. 2017 May;26(5):2519-2532. doi: 10.1109/TIP.2017.2671921. Epub 2017 Feb 20.
5
Perceptual Quality Assessment for Multi-Exposure Image Fusion.多曝光图像融合的感知质量评估。
IEEE Trans Image Process. 2015 Nov;24(11):3345-56. doi: 10.1109/TIP.2015.2442920. Epub 2015 Jun 9.
6
High dynamic range image compression by optimizing tone mapped image quality index.通过优化色调映射图像质量指数实现高动态范围图像压缩。
IEEE Trans Image Process. 2015 Oct;24(10):3086-97. doi: 10.1109/TIP.2015.2436340.
7
Exposure fusion using boosting Laplacian pyramid.利用提升拉普拉斯金字塔进行曝光融合。
IEEE Trans Cybern. 2014 Sep;44(9):1579-90. doi: 10.1109/TCYB.2013.2290435.
8
Image fusion with guided filtering.基于导向滤波的图像融合。
IEEE Trans Image Process. 2013 Jul;22(7):2864-75. doi: 10.1109/TIP.2013.2244222. Epub 2013 Jan 30.
9
Gradient-directed multiexposure composition.梯度引导的多曝光合成。
IEEE Trans Image Process. 2012 Apr;21(4):2318-23. doi: 10.1109/TIP.2011.2170079. Epub 2011 Sep 29.
10
Generalized random walks for fusion of multi-exposure images.广义随机游走融合多曝光图像。
IEEE Trans Image Process. 2011 Dec;20(12):3634-46. doi: 10.1109/TIP.2011.2150235. Epub 2011 May 5.