[1]贾存坤,戴声奎,卫志敏.采用亮通道先验的低照度图像增强算法[J].华侨大学学报(自然科学版),2018,39(4):595-599.[doi:10.11830/ISSN.1000-5013.201605078]
　JIA Cunkun,DAI Shengkui,WEI Zhimin.Low Light Image Enhancement Algorithm Using Bright Channel Prior[J].Journal of Huaqiao University(Natural Science),2018,39(4):595-599.[doi:10.11830/ISSN.1000-5013.201605078]
点击复制

采用亮通道先验的低照度图像增强算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第39卷
期数:
2018年第4期
页码:
595-599
栏目:
出版日期:
2018-07-18

文章信息/Info

Title:
Low Light Image Enhancement Algorithm Using Bright Channel Prior
文章编号:
1000-5013(2018)04-0595-05
作者:
贾存坤;  戴声奎;  卫志敏
1. 华侨大学 信息科学与工程学院, 福建 厦门 361021;2. 厦门市移动多媒体通信重点实验室, 福建 厦门 361021
Author(s):
JIA Cunkun;  DAI Shengkui;  WEI Zhimin
1. School of Information Science and Engineering, Huaqiao University, Xiamen 361021, China; 2. Xiamen Key Laboratory of Mobile Multimedia Communication, Xiamen 361021, China
关键词:
图像增强算法;  亮通道先验;  引导滤波;  自适应对数校正;  HSV彩色空间;  Retinex理论
Keywords:
image enhancement algorithm;  bright channel prior;  guided filter;  adaptive logarithm correction;  HSV color space;  Retinex theory
分类号:
TP391.9
DOI:
10.11830/ISSN.1000-5013.201605078
文献标志码:
A
摘要:
针对低照度彩色图像亮度偏低、对比度差等问题,提出基于亮通道先验的低照度图像增强算法.首先,分析Retinex算法所存在的缺陷,提出了亮通道先验.然后,将原RGB彩色图像转换到HSV彩色空间,对亮度分量V使用亮通道先验和引导滤波估计光照分量和反射分量,并且采用自适应对数校正对光照分量进行提升.最后,将增强后的图像转换到RGB彩色空间.实验结果表明:该算法快速有效,能够很好地提升图像整体亮度和对比度,图像细节得到增强,克服了颜色失真和光晕等问题,增强后的彩色图像更为明亮、自然.
Abstract:
In order to improve the brightness and contrast of low illumination image, a low light image enhancement algorithm based on bright channel prior is proposed in this paper. Firstly, the proposed algorithm comes up with bright channel prior in order to deal with flaw of the Retinex algorithms. Then the original RGB color image is converted to HSV color space, and the illumination image of V component is evaluated by using bright channel and guided filter, as well as the contrast of the illumination image is enhanced by adaptive logarithm correction. Finally, the enhanced image is converted to RGB color space. The experimental results show that the proposed algorithm is fast and effective, the overall image brightness and contrast is increased, as well as the image detail. Furthermore, the proposed algorithm overcome the color distortion and halos, and the enhanced color image is more bright and beautiful.

参考文献/References:

[1] LAND E H,MCCANN J J.Lightness and retinex theory[J].J Opt Soc Am,1971,61(1):1-11.
[2] BRAINARD D H,WANDELL B A.Analysis of the retinex theory of color vision[J].J Opt Soc Am A,1986,3(10):1651-1661.DOI:10.1364/JOSAA.3.001651.
[3] FAUGERAS O D.Digital color image processing within the framework of a human visual model[J].IEEE Transactions on Acoustics, Speech and Signal Processing,1979,27(4):380-393.DOI:10.1109/TASSP.1979.1163262.
[4] HORN B K.Determining lightness from an image[J].Computer Graphics and Image Processing,1974,3(4):277-299.DOI:10.1016/0146-664X(74)90022-7
[5] JOBSON D J,RAHMAN Z,WOODELL G A.Properties and performance of a center/surround retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462.DOI:10.1109/83.557356.
[6] JOBSON D J,RAHMAN Z,WOODELL G A.A multiscale retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing,1997,6(7):965-976.
[7] ELAD M.Retinex by two bilateral filters[C]//International Conference on Scale-Space Theories in Computer Vision.Berlin:Springer-Verlag,2005:217-229.DOI:10.1007/11408031_19.
[8] HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.DOI:10.1109/TPAMI.2012.213.
[9] PEI S C,LEE T Y.Nighttime haze removal using color transfer pre-processing and dark channel prior[C]//19th IEEE International Conference on Image Processing.[S.l.]:IEEE Press,2012:957-960.
[10] 王晓.基于Retinex理论的图像颜色校正算法[D].西安:西安电子科技大学,2014:81-82.
[11] 赵晓霞.基于 RETINRX 理论的视频图像增强系统研究[D].北京:中国矿业大学,2011:30-45.

备注/Memo

备注/Memo:
收稿日期: 2016-05-24
通信作者: 戴声奎(1971-),男,副教授,博士,主要从事图像处理、视频分析和模式识别的研究.E-mail:D.S.K@126.com.
基金项目: 福建省科技计划重点项目(2013H0030); 中央高校基本科研业务费专项基金资助项目(JB-ZR1145); 华侨大学研究生科研创新能力培育计划资助项目(1400401015)
更新日期/Last Update: 2018-07-20