Giter Site home page Giter Site logo

twotu / mf-lime Goto Github PK

View Code? Open in Web Editor NEW
64.0 3.0 9.0 69.24 MB

基于Retinex模型和多尺度融合的低光照图像增强技术 Low-light image enhancement technology based on Retinex model and multi-scale fusion

License: MIT License

MATLAB 77.11% C 22.89%
image-processing low-light-image-enhancement mulit-scale retinex

mf-lime's Introduction

MF-LIME

基于Retinex模型和多尺度融合的低光照图像增强技术

Low-light image enhancement technology based on Retinex model and multi-scale fusion

实验环境


本项目基于Zhang等人《A New Underwater Image Enhancing Method via Color Correction and Illumination Adjustment》论文中提出的亮度调整流程和Codruta O. Ancuti等人《Color Balance and Fusion for Underwater Image Enhancement》论文中提出的多尺度融合框架相结合的低光照图像增强技术。

Abstract

提出了一种亮度调整、锐化和多尺度融合相结合的算法。首先对原图像分解出光照图,基于Retinex模型进行估计,并进行伽马矫正,得到亮度均衡的图像;为补偿伽马矫正导致过曝区域的细节丢失,对原图像进行锐化处理,以提升图像细节部分;最后在多尺度融合金字塔模型下,根据计算两个输入图像的权重进行多尺度融合,得到最终的增强图像。此外,还计算了五个非参考图像质量评价指标(BRISQUE,CEIQ,ENIQA,NIQE,PIQE)。


项目文件说明

  • main.m:本项目主程序入口,处理一张图像,并计算五个非参考图像质量评价指标。
  • IQA_data.m:本项目处理一个数据集的图像,并计算五个非参考图像质量评价指标平均值。

Datasets

  • DICM数据集 ,共69张图像,只选取了前44张低光照图像。
  • Fusion数据集 ,16张低光照图像。
  • LIME数据集 ,10张低光照图像。
  • VV数据集 ,共有24张图像,只选取了前22张低光照图像,未计入2张测试图像。

images

  • 用华为P40相机拍摄的15张低光照图像。

IQA

非参考图像质量评价指标(CEIQENIQA)的项目文件,点击即可查看该指标Github项目源。指标(BRISQUE,NIQE,PIQE)MATLAB图像处理工具箱自带,直接调用即可。

  • BRISQUE:基于自然场景统计的失真通用非参考图像质量评估模型。
  • CEIQ:基于对比度增强的失真图像非参考质量评价指标。
  • ENIQA:基于图像熵的高性能通用非参考图像质量评估指标。
  • NIQE:从自然场景图像计算的默认模型进行比较的非参考图像质量评估模型。
  • PIQE:基于感知的非参考图像质量评估器。

ours

本项目 .m 函数文件夹

Test

低光照图像增强领域各方法对比,具体说明见文件夹下README.md文件。


实验结果

  • 各方法主观对比

  • 各方法客观评价

Citations

@inproceedings{8305027, 
  author={W. Zhang and G. Li and Z. Ying}, 
  booktitle={2017 IEEE Visual Communications and Image Processing (VCIP)}, 
  title={A new underwater image enhancing method via color correction and illumination adjustment}, 
  year={2017},  
  pages={1-4}, 
  doi={10.1109/VCIP.2017.8305027},
}
@inproceedings{
  title={Color Balance and Fusion for Underwater Image Enhancement},
  author={C. O. Ancuti, C. Ancuti, C. De Vleeschouwer and P. Bekaert},
  booktitle={in IEEE Transactions on ImageProcessing,
  volume={27},
  pages={379-393},
  month = {Jan},
  year={2018}
}

@InProceedings{Ying_2017_ICCV,
  author = {Ying, Zhenqiang and Li, Ge and Ren, Yurui and Wang, Ronggang and Wang, Wenmin},
  title = {A New Low-Light Image Enhancement Algorithm Using Camera Response Model},
  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
  month = {Oct},
  year = {2017}
}
@article{fu2016mf,
  title={A fusion-based enhancing method for weakly illuminated images},
  author={Fu, Xueyang and Zeng, Delu and Huang, Yue and Liao, Yinghao and Ding, Xinghao and Paisley, John},
  journal={Signal Processing},
  volume={129},
  pages={82--96},
  year={2016},
  publisher={Elsevier}
}
@inproceedings{
  title={LIME: Low-light Image Enhancement via Illumination Map Estimation},
  author={Guo X , Yu L , Ling H},
  booktitle={IEEE Transactions on Image Processing},
  pages={1-1},
  year={2016},
  organization={IEEE}
}
@inproceedings{dong2011fast,
  title={Fast efficient algorithm for enhancement of low lighting video},
  author={Dong, Xuan and Wang, Guan and Pang, Yi and Li, Weixin and Wen, Jiangtao and Meng, Wei and Lu, Yao},
  booktitle={2011 IEEE International Conference on Multimedia and Expo},
  pages={1--6},
  year={2011},
  organization={IEEE}
}

mf-lime's People

Contributors

twotu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

mf-lime's Issues

论文找不到

您好,这篇论文我没有找到,您给的英文和中文名称找不到对应的论文

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.