一种改进的暗通道先验水下彩色图像复原算法  

Underwater color image restoration algorithm based on improved prior dark-channel model

作　　者：胡学龙[1] 张文 胡铸鑫[2] 陆慧敏[3] HU Xuelong;ZHANG Wen;HU Zhuxin;LU Huimin(Information Engineering College,Yangzhou University,Yangzhou 225127,China;College of Teacher Education,Wenzhou University,Wenzhou 325035,China;Department of Mechanical&Control Engineering,Kyushu Institute of Technology,Kitakyushu 8048550,Japan)

机构地区：[1]扬州大学信息工程学院,江苏扬州225127 [2]温州大学教师教育学院,浙江温州325035 [3]九州工业大学工学研究院机械控制工程系,福冈北九州8048550

出　　处：《扬州大学学报（自然科学版）》2018年第4期37-41,共5页Journal of Yangzhou University：Natural Science Edition

基　　金：江苏高校自然科学基金资助项目(15KJB510032);江苏省"六大人才高峰"第七批高层次人才资助项目(2014-DZXX-149);同济大学海洋地质国家重点实验室开放课题资助项目(MGK1608;MGK1803)

摘　　要：为了解决光在水下传播过程中能量散射和衰减所导致水下图像对比度较低、纹理细节模糊和颜色失真等问题,提出一种改进暗通道先验水下彩色图像复原算法,根据水下光线传播特性建立水下图像成像模型,将水下图像的去模糊和颜色校正相结合,应用改进的暗通道先验算法提高水下彩色图像的对比度,再通过白平衡颜色复原方法处理水下彩色图像,实现水下彩色图像的颜色校正.实验结果表明,本文算法能够提高水下彩色图像的对比度,有效恢复水下图像的颜色.Due to the problem of low contrast,texture blur and color distortion caused by scattering and attenuation of the light in underwater environment,this paper proposes an underwater color image restoration algorithm based on improved prior dark-channel model.According to the imaging model of underwater image,it combines deblurring and color correction.Then the details of underwater color image is enhanced by the improved prior dark-channel model and the color of the underwater image is corrected by white balance.The experimental results show that the proposed algorithm effectively improves the visual quality of the underwater image and restores the color of the image.

关 键 词：水下图像 图像复原 暗通道先验 白平衡 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]