为了解决水下图像模糊和偏色的问题,在水下图像成像模型的基础上提出水下图像复原算法.利用白平衡算法对图像进行色彩调整,计算图像的暗通道图,通过暗通道图估计图像的背景光强度.对于非深海区域的图像,若图像包含水体,则根据水体的颜色和纹理特征提取出图像中的水体部分,利用光在水中的衰减公式计算图像3个通道透射率之间的关系;若图像不包含水体,则根据3个通道直方图的分布计算透射率之间的关系.根据暗通道先验的原理,计算出3个通道的透射率图,使用引导滤波对透射率图进行细化.根据计算出的背景光强度和透射率对图像进行复原.对于采用人工照明的深海图像,采用修正的公式进行处理.实验结果表明,在图像清晰度的评价中,该算法优于对比算法,具有较好的鲁棒性.%An underwater image restoration algorithm was proposed based on underwater image model in order to solve the problems of underwater image blurring and color cast.The algorithm used the white balance algorithm to adjust the color of the image and calculated the dark channel image of the original image.Then the background light intensity of the image was estimated by the dark channel map.For the image of the non-deep region,if the image contained water body,the water body part of the image was extracted according to the color and texture features.Then the relation of three channels' transmission was calculated by using the light attenuation formula in water.If the image did not contain the water body,the transmittance of the three channels was calculated according to the distribution of the three channel histograms.The transmission map of the three channels was calculated according to the principle of the dark channel priori,and the guide filter was used to refine the transmission map.The image was restored according to the value of background light intensity and transmission map.The modified formula was adopted for deep sea images with artificial illumination.Experimental results show that the algorithm is superior to the contrast algorithm in image clarity evaluation and has good robustness.
展开▼
