亮通道先验Retinex对低照度图像的光照补偿

李赓飞; 李桂菊; 韩广良; 刘培勋; 江山

doi:10.3788/OPE.20182605.1191

您当前的位置：

首页 >

文章列表页 >

亮通道先验Retinex对低照度图像的光照补偿

信息科学 | 更新时间：2020-08-13

- 亮通道先验Retinex对低照度图像的光照补偿
- Illumination compensation using Retinex model based on bright channel prior
- 光学精密工程 2018年26卷第5期页码：1191-1200
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国科学院大学, 北京 100049
- 作者简介：
  
  [ "李赓飞(1989-), 男, 吉林通化人, 博士研究生, 2012年于吉林大学获得学士学位, 主要从事图像和视频信息处理研究。E-mail:killcolours@126.com" ]
  [ "李桂菊(1964-), 女, 吉林吉林人, 研究员, 博士生导师, 主要从事图像和视频信息处理、DSP开发与应用研究。E-mail:lgjciom666@126.com" ]
- 基金信息：
  
  国家自然科学基金资助项目(61401425);国家自然科学基金资助项目(61602432)
- DOI：10.3788/OPE.20182605.1191
  中图分类号：
- 收稿日期：2017-08-21，
  
  录用日期：2017-9-26，
  
  纸质出版日期：2018-05-25
- 稿件说明：
移动端阅览
李赓飞, 李桂菊, 韩广良, 等. 亮通道先验Retinex对低照度图像的光照补偿[J]. 光学精密工程, 2018,26(5):1191-1200.

Geng-fei LI, Gui-ju LI, Guang-liang HAN, et al. Illumination compensation using Retinex model based on bright channel prior[J]. Optics and precision engineering, 2018, 26(5): 1191-1200.
李赓飞, 李桂菊, 韩广良, 等. 亮通道先验Retinex对低照度图像的光照补偿[J]. 光学精密工程, 2018,26(5):1191-1200. DOI： 10.3788/OPE.20182605.1191.

Geng-fei LI, Gui-ju LI, Guang-liang HAN, et al. Illumination compensation using Retinex model based on bright channel prior[J]. Optics and precision engineering, 2018, 26(5): 1191-1200. DOI： 10.3788/OPE.20182605.1191.

摘要

针对光照不足导致图像质量退化的问题，提出了亮通道先验的Retinex算法用来补偿图像的光照强度。该算法假设局部恒常的光照可以初步满足光照均匀并与场景相似，以亮通道运算对光照分量进行粗估计；通常解决局部处理带来的分块效应问题是采用引导滤波方法，但这会使补偿后的图像纹理模糊甚至丢失细节，为此设计了基于图像结构相似性的融合策略。最后使用Retinex理论模型对光照进行补偿。实验结果表明：所提算法简单高效，能够对图像阴影或夜间图像的低照度区域进行快速地光照补偿，在峰值信噪比（PNSR）上较传统算法提高了5 dB左右，在结构相似性（SSIM）上比传统算法提高了7%以上。算法在纯软件系统的PC机上处理640×360的彩色视频时能达到6~12 ms/帧，处理320×256的红外视频时达到4~10 ms/帧，可满足工程需要。

Abstract

Aiming at the problem of image quality degradation caused by insufficient illumination

a retractive algorithm of bright channel was proposed to compensate the illumination intensity of the image. The algorithm assumed that the local constant light could initially satisfy the uniformity of illumination and was similar to the scene

and the bright channel operation was used to estimate the weight of the light component. The problem of blocking was usually solved by the local processing

but this would make the compensation image texture blurred or even lost

and the fusion strategy based on image structure similarity was designed. Finally

the Retinex theoretical model was used to compensate for the light. The experimental results show that the proposed algorithm is simple and efficient

and can compensate for the low illumination area of image shadows or nighttime images. Compared with the traditional algorithm

the peak signal to noise ratio (PNSR) is improved by about 5 dB and the structure similarity (SSIM) increased by more than 7%. The algorithm in the pure software system PC (CPU frequency 2.4 G) processing 640×360 color video can reach 6-12 ms/frame

processing 320×256 infrared video to reach 4-10 ms/frame

to meet the needs of the project.

关键词

Keywords

references

聂祥飞, 谭泽富, 郭军.应用小波变换的人脸光照补偿[J].光学精密工程, 2008, 16(1):150-155.

NIE X F, TAN Z F, GUO J. Face illumination compensation basedon wavelet transform[J]. Opt. Precision Eng., 2008, 16(1):150-155. (in Chinese)

龚卫国, 杨利平, 辜小花, 等.基于多级小波分解的人脸图像光照补偿方法[J].光学精密工程, 2008, 16(8):1459-1464.

GONG W G, YANG L P, GU X H, et al .. Illumination compensation based on multi-level wavelet decomposition for face recognition[J]. Opt. Precision Eng., 2008, 16(8):1459-1464. (in Chinese)

LAND E H, MCCANN J J. Lightness and Retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1):1-11.

LAND E H. Recent advances in Retinex theory and some implications for cortical computations:Color vision and the natural image[J]. Proceedings of the National Academy of Sciences of the United States of America, 1983, 80(16):5163-5169.

JOBSOND 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.

JOBSOND 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.

KIMMELR, ELAD M, SHAKED D, et al .. A variational framework for retinex[J]. International Journal of Computer Vision, 2003, 52(1):7-23.

马忠丽, 文杰.融合边缘信息的单尺度Retinex海雾去除算法[J].计算机辅助设计与图形学学报, 2015, 27(2):217-225.

MA ZH L, WEN J. Single-scale Retinex sea fog removal algorithm fused the edge information[J]. Journal of Computer-Aided Design & Computer Graphics, 2015, 27(2):217-225. (in Chinese)

ZHANG SH, WANG T, DONG J Y, et al .. Underwater image enhancement via extended multi-scale Retinex[J]. Neurocomputing, 2017, 245:1-9.

BISWASB, ROY P, CHOUDHURI R, et al .. Microscopic image contrast and brightness enhancement using multi-scale Retinex and Cuckoo search algorithm[J]. Procedia Computer Science, 2015, 70:348-354.

WANG Y F, WANG H Y, YIN CH L, et al .. Biologically inspired image enhancement based on Retinex[J]. Neurocomputing, 2016, 177:373-384.

LIN H N, SHI ZH W. Multi-scale Retinex improvement for nighttime image enhancement[J]. Optik, 2014, 125(24):7143-7148.

余顺园, 朱虹.夜间有雾图像的光照模型构建及去雾[J].光学精密工程, 2017, 25(3):729-734.

YU SH Y, ZHU H. Lighting model construction and haze removal for nighttime image[J]. Optics and Precision Engineering, 2017, 25(3):729-734. (in Chinese)

CHANG H B, NG M K, WANG W, et al .. Retinex image enhancement via a learned dictionary[J]. Optical Engineering, 2015, 54(1):013107.

LAN X, ZUO ZH Y, SHEN H F, et al .. Framelet-based sparse regularization for uneven intensity correction of remote sensing images in a retinex variational framework[J]. Optik, 2016, 127(3):1184-1189.

WANG G D, DONG Q, PAN ZH K et al .. Retinex theory based active contour model for segmentation of inhomogeneous images[J]. Digital Signal Processing, 2016, 50:43-50.

SOBOLR. Improving the Retinex algorithm for rendering wide dynamic range photographs[J]. Journal of Electronic Imaging, 2004, 13(1):65-74.

HEK M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.

FATTALR. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3):1-9.

HEK M, SUN J. Fast guided filtering[Z]. arXiv preprint arXiv: 150500996, 2015: 1-2.

SETIAWANA W, MENGKO T R, SANTOSO O S, et al .. Color retinal image enhancement using CLAHE[C]//Proceedings of 2013 International Conference on ICT for Smart Society . IEEE, 2013, 7979: 1-3.

浏览量

472

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合改进Retinex及自适应分数阶微分的雾霾公路交通图像增强

多图像融合Retinex用于弱光图像增强

结合Retinex校正和显著性的主动轮廓图像分割

光学显微线条纹图像中心线提取

基于多尺度Retinex的数字X光图像增强方法研究