一种结合暗通道先验和图像融合的水下图像复原算法  

Underwater Image Restoration Method Based on Dark Channel Prior and Image Fusion

作　　者：尹芳[1,2] 陈田田[1] 吴锐[3] 付自如 于晓洋[2] 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080 [2]哈尔滨理工大学仪器科学与技术博士后科研流动站,哈尔滨150080 [3]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001

出　　处：《小型微型计算机系统》2017年第11期2591-2596,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61440025)资助;黑龙江省教育厅科学技术研究项目(12541119)资助

摘　　要：针对一般水下图像增强方法易使得图像失真,颜色过饱和,传统的去雾方法用于水下图像复颜色偏暗等问题,本文提出基于暗通道和图像融合的水下图像复原方法.首先根据水下成像特点,建立水下光学成像模型,利用水下图像光学成像模型与大气模型相似的特点,修正背景光值,利用优化的暗通道先验算法对图像进行清晰化处理得到复原图像.其次,用直方图均衡化方法对水下图像进行提高对比度、色彩平衡处理得到增强图像.最后,根据对水下复原图像和增强图像的特点进行像素级融合.实验结果证明,该方法在保留图像细节信息的同时,提高图像清晰度和对比度,修正色彩不平衡.Underwater image enhancement method is easy to make the image distortion,color oversaturation. And image color is dim when traditional image dehazing method is used to underwater. So,underwater image restoration based on dark channel prior and image fusion is proposed. Firstly,according to the characteristics of underwater imaging,underwater optical imaging model is established.Underwater optical imaging model is similar to the atmosphere model. Global light is corrected. The edge contour and texture clearer in the object when underwater image restoration based on dark channel prior is used. But the image contrast is low,the color is dim. Secondly,the histogram equalization method is applied to underwater image enhancement,the results are higher contrast,and color balance. But some details information of the image is lost,edges and textures of objects is blurrier. The image fusion between the underwater restoration image and enhancement image is performed. Experimental results show that the method preserves image details while improves image sharpness and contrast,corrects color imbalance.

关 键 词：图像处理 暗通道先验 直方图均衡化 图像融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]