基于暗原色先验模型的水下彩色图像增强算法

J4 ›› 2016, Vol. 33 ›› Issue (2): 140-147.

基于暗原色先验模型的水下彩色图像增强算法

曹美,盛惠兴,李庆武,程亚玲,周妍

1 河海大学物联网工程学院，江苏常州，213022； 2 常州市传感网与环境感知重点实验室，江苏常州，213022

收稿日期:2015-03-27 修回日期:2015-07-13 出版日期:2016-03-28 发布日期:2016-03-28
通讯作者: 盛惠兴 (1961-)，江苏人，硕士，副教授，从事图像处理及模式识别方面的研究工作. E-mail:Sheng_hx@139.com
作者简介:曹美 (1989-),安徽人，硕士生，从事图像处理及模式识别方面的研究工作，E-mail:caomei_vip@126.com
基金资助:
国家自然科学基金（ 60972101, 41306089）；江苏省自然科学基金 (BK20130240)

Underwater color image enhancement algorithm based on prior dark-channel model

CAO Mei,SHENG Huixing,LI Qingwu,CHENG Yaling,ZHOU Yan

1.College of Internet of Things Engineering, Hohai University, Changzhou 213022, China; 2. Changzhou Key Laboratory of Sensor Networks and Environmental Sensing, Changzhou 213022, China

Received:2015-03-27 Revised:2015-07-13 Published:2016-03-28 Online:2016-03-28

摘要/Abstract

摘要： 针对在水下环境中，光的散射和衰减导致水下光学成像质量严重下降，图像对比度低、颜色失真的问题，提出了一种暗原色先验和基于通道直方图量化的颜色校正算法相结合的图像增强新方法。对于待增强的水下彩色图像，首先建立水下光学图像成像模型，并利用优化与改进的暗原色先验算法对图像进行去模糊，然后通过分析R、G、B三通道的累积直方图，对去模糊后的彩色图像各通道灰度值进行量化，实现图像的颜色校正。实验结果表明，提出的方法可以有效地消除了由于光的散射造成图像的模糊，有效提高了水下图像的视觉效果，恢复水下图像的颜色平衡。

关键词: 图像处理；水下彩色图像增强；暗原色先验；颜色平衡

Abstract: Considering the problems of low contrast and color distortion caused by scattering and attenuation of the light in the underwater environment, the underwater color image enhancement method is presented in this paper, which integrated dark channel prior and the color correction algorithm based on channel histogram quantization. Firstly, for the underwater color image to be enhanced, underwater optical imaging model is established and the optimized and improved dark channel prior algorithm is used for image deblurring. Then, by analyzing the cumulative histogram of the deblurring image R, G, B three channels, the gray value of the each channel is quantified to achieve color correction of the image. The experimental results show that the proposed method can effectively eliminate the image blur caused by the scattering of light, improve the visual quality of the underwater image and restore color balance of the underwater image.

Key words: image processing; underwater color image enhancement; dark channel prior; color balance

中图分类号:

TP394.1

曹美盛惠兴李庆武程亚玲周妍. 基于暗原色先验模型的水下彩色图像增强算法[J]. J4, 2016, 33(2): 140-147.

CAO Mei,SHENG Huixing,LI Qingwu,CHENG Yaling,ZHOU Yan. Underwater color image enhancement algorithm based on prior dark-channel model[J]. J4, 2016, 33(2): 140-147.

参考文献

[1] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[C]. IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA:IEEE Press, 2009: 1956-1963．
[2] 李庆武, 束代群, 周妍等. 水下光学图像成像清晰化研究[J]. 光学学报. 2014, 34: s110001-1-s110001-6.
[3] 杨淼, 纪志成. 基于模糊形态筛和四元数的水下彩色图像增强[J].仪器仪表学报. 2012, 33(7) :1601-1605.
[4] John Y. Chiang, Ying-Ching Chen. Underwater Image Enhancement by Wavelength Compensation and Dehazing[J]. IEEE Transactions On Image Processing, 2012, 21(4), 1756-1769.
[5] Cosmin Ancuti, Codruta Orniana Ancuti. Enhancing Underwater Images and Videos by Fusion[J]. IEEE Computer Vision and Pattern Recognition.2012.
[6] Seiichi Serikawa, Huimin Lu. Underwater image dehazing using joint trilateral filter[J]. Computers and Electrical Engineering.2014, 40:41-50.
[7] Liu C, Wang M. Removal of water scattering[C]. International Conference on Computer Engineering and Technology.2010,2.
[8] Viuliu, D Carrick, R Daniela, Color accurate underwater imaging using perceptual adaptive illumination[J]. Autonomous Robots. 2010,31(2):285-292.
[9] 孙小明,孙俊喜,赵立荣等暗原色先验单幅图像去雾改进算法[J].中国图像图形学报.2010,19(3):381-385.
[10] 汪荣贵, 傅剑峰, 杨志学等. 基于暗原色先验模型的Retinex算法[J]. 电子学报. 2013, 6: 1188-1192
[11] 纪则轩, 陈强, 孙权森等. 基于双边滤波的单尺度Retinex图像增强算法[J]. 微电子学与计算机. 2009, 26(10): 99-102.
[12]张冰冰,戴声奎,孙万源. 基于暗原色先验模型的快速去雾算法[J]. 中国图象图形学报. 2013, 18(2): 184-188.
[13] 郭永刚, 葛庆平, 郭楠. 利用白平衡进行偏色图像的颜色校正[J]. 计算机工程与应用.2005, 20:56-59.
[14] 刘海波, 汤群芳, 杨杰. 改进直方图均衡和Retinex算法在灰度图像增强中的应用[J]. 量子电子学报. 2014,31(5): 525-532.