基于暗原色先验模型的Retinex算法

doi:10.3969/j.issn.0372-2112.2013.06.022

电子学报 ›› 2013, Vol. 41 ›› Issue (6): 1188-1192.DOI: 10.3969/j.issn.0372-2112.2013.06.022

基于暗原色先验模型的Retinex算法

汪荣贵, 傅剑峰, 杨志学, 沈法琳, 查炜

合肥工业大学计算机与信息学院, 安徽合肥 2310009

收稿日期:2011-08-02 修回日期:2012-05-02 出版日期:2013-06-25
- 通讯作者:
- 傅剑峰男,1987年出生于安徽芜湖,合肥工业大学计算机与信息学院硕士研究生,主要研究方向为智能视频处理与分析、车载视觉增强系统、多媒体技术. E-mail:fjfeng1987@126.com
- 作者简介:
- 汪荣贵男,1966年出生于安徽池州,计算机应用技术专业博士,合肥工业大学计算机与信息学院教授,博士生导师,中国计算机学会高级会员,主要研究方向为智能视频处理与分析、车载视觉增强系统、多媒体技术.
- 基金资助:
- 国家自然科学基金 (No.60175032); 中央高校基本科研业务费专项资金 (No.2012HGCX0001)

A Novel Retinex Algorithm Based on Dark Channel Prior Model

WANG Rong-gui, FU Jian-feng, YANG Zhi-xue, SHEN Fa-lin, ZHA Wei

School of Computer and Information, Hefei University of Technology, Hefei, Anhui 2310009, China

Received:2011-08-02 Revised:2012-05-02 Online:2013-06-25 Published:2013-06-25

摘要/Abstract

摘要： 现有雾天图像增强的Retinex算法采用固定滤波器,无法适应多种景深和雾化程度的情况.对此,本文提出一种基于暗原色先验模型的Retinex算法.暗原色先验模型反映了雾天图像中雾的分布与景深信息.受此启发,根据局部区域暗原色值设计一种尺度可变滤波器,针对不同景深和雾化区域采用不同尺度的滤波器估算雾天图像的照度分量,实现对雾天图像的增强.分别使用主观观察和客观数据分析方法,将本文算法与HE算法、固定尺度MSR算法进行对比,本文算法在细节增强以及图像整体效果上均优于HE算法和固定尺度MSR算法.

关键词: 雾天图像增强, Retinex算法, 暗原色先验模型, HE算法, MSR算法

Abstract: Current Retinex algorithm applied in foggy image enhancement with fixed filter can't adapt to the situation of various depth of field and atomization.This paper presents a self-adaptive filter Retinex algorithm based on dark channel prior model.The model of dark channel prior reflects the information of field depth and distribution of atmosphere in foggy image.We are inspired to design an self-adaptive filter according to the local value of dark channel using different filters in different depth of field and foggy area to estimate the illumination component of the image,and to achieve the clarity of foggy image.Finally,we compare the result of the proposed algorithm with the result of HE algorithm and result of fixed filter MSR algorithm using the subjective observation and objective data analysis method.The comparison shows that the result of Retinex algorithm based on dark channel prior has better detail of image and global effect than that of the HE algorithm and fixed filter MSR algorithm.

Key words: foggy image enhancement, Retinex algorithm, dark channel prior model, HE algorithm, MSR algorithm

中图分类号:

TP391.41

汪荣贵, 傅剑峰, 杨志学, 沈法琳, 查炜. 基于暗原色先验模型的Retinex算法[J]. 电子学报, 2013, 41(6): 1188-1192.

WANG Rong-gui, FU Jian-feng, YANG Zhi-xue, SHEN Fa-lin, ZHA Wei. A Novel Retinex Algorithm Based on Dark Channel Prior Model[J]. Acta Electronica Sinica, 2013, 41(6): 1188-1192.

参考文献

[1] GONZAEL R C.Digital Image Processing[M](2nd ed).Beijing:Publishing House of Electronics Iudustry,2003.460-521.

[2] 陈桂友,孙同景,雷印胜.一种基于自适应滤波的指纹图像增强算法[J].电子测量与仪器学报,2006,20(6):76-80. Chen G Y,Sun T J,Lei Y S.Fingerprint image enhancement based on adaptive filter[J].Journal of Electronic Measurement and Instrument,2006,20(6):76-80.(in Chinese)

[3] 王健,陈启美,章德.CMOS图像实时增强预处理研究及实现[J].仪器仪表学报,2007,28(1):48-52. Wang J,Chen Q M,Zhang D.Study on real-time image enhancement pre-processing for CMOS sensor[J].Chinese Journal of Scientific Instrument,2007,28(1):48-52.(in Chinese)

[4] Rahman Z,Jobson D J,Woodell G A,Hines G D.Image enhancement,image quality,and noise[A].Proceedings of the Photonic Devices and Algorithms for Computing VII[C].San Diego:SPIE,2005.164-178.

[5] 芮义斌,李鹏,孙锦涛.一种图像去薄雾方法[J].计算机应用,2006,26(1):154-156. Rui Yibin,Li Peng,Sun Jintao.Method of removing fog effect from images[J].Journal of Computer Applications,2006,26(1):154-156.(in Chinese)

[6] Rahman Z,Jobson D J,Woodell G A.Multi-scale retinex for color image enhancement[A].Proceedings of the International Conference on Image Processing.Lausanne[C].Switzerland:IEEE Press,1996.1003-1006.

[7] 陈雾.基于Retinex理论的图像增强算法研究[D].南京:南京理工大学,2006. Chen Wu.Image Enhancement Based on Retinex Theory[D].Nanjing:Nanjing University of Science and Technology,2006.(in Chinese)

[8] 王大雷.雾天图像增强技术的分析与研究[D].南京:南京理工大学,2007. Wang Dalei.Analyze and Research on Foggy Image Enhancement[D].Nanjing:Nanjing University of Science and Technology,2007.(in Chinese)

[9] 汪荣贵、张璇.一种新型自适应Retinex 图像增强方法研究[J].电子学报,2010,38(12):2933-2936. Wang Ronggui,Zhang Xuan.A novel adaptive Retinex algorithm for image enhancement[J].Acta Electronica Sinica,2010,38(12):2933-2936.(in Chinese)

[10] 汪荣贵,朱静,杨万挺,方帅.基于照度分割的局部多尺度Retinex算法[J].电子学报,2010,38(5):1181-1186. Wang Ronggui,Zhu Jing,Yang Wangting,Fang Shuai.An improved local multi-scale Retinex algorithm based on illuminance image segmentation[J].Acta Electronica Sinica,2010,38(5):1181-1186.(in Chinese)

[11] 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.

[12] Kaiming He,Jian Sun,Xiaoou Tang.Single image haze removal using dark channel prior[A].CVPR 2009[C].Miami,Florida:IEEE,2009.1956-1963.

[13] Levin A,Lischinski D,Weiss Y.A closed form solution to natural image matting[A].CVPR 2006[C].New York:IEEE,2006.61-68.

基于暗原色先验模型的Retinex算法

A Novel Retinex Algorithm Based on Dark Channel Prior Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

[1]	汪荣贵;朱静;杨万挺;方帅;张新彤. 基于照度分割的局部多尺度Retinex算法[J]. 电子学报, 2010, 38(5): 1181-1186.
[2]	汪荣贵;张璇;张新龙;傅剑峰. 一种新型自适应Retinex图像增强方法研究[J]. 电子学报, 2010, 38(12): 2933-2936.