基于暗通道先验改进算法的水下图像增强方法研究

Underwater Image Enhancement Based on Improved Algorithm of Dark Channel Prior

针对水下图像受介质散射和吸收的影响所出现的颜色失真、对比度低和细节模糊等问题,提出水下图像增强的暗通道先验改进算法。采用白平衡处理对水下图像的蓝(绿)色偏进行颜色校正,进而在LAB空间对图像L分量进行同态滤波处理,从而获得暗部细节提亮的图像。在RGB空间对图像分别进行CLAHE处理增强图像对比度,解决图像雾化问题,MSRCR处理提高图像色彩饱和度并均衡图像亮度。根据暗通道先验图像计算融合权重系数对所得到的3幅图像进行加权融合与细节增强,得到最终增强图像。实验结果表明,所提算法能够有效消除图像颜色失真情况,增强的图像呈现出高对比度和更清晰的细节。

In order to solve the problems of color distortion,low contrast and fuzzy details of underwater images caused by medium scattering and absorption,an improved algorithm of dark channel prior for underwater image enhancement is proposed.White balance processing is adopted to correct the blue(green) color deviation of the underwater image,and homomorphic filtering is conducted on the L component of the image in LAB space,so as to obtain a dark detail highlighted image.In RGB space,CLAHE processing is conducted to enhance the image contrast and solve the image atomization problem,and MSRCR processing is conducted to improve image color saturation and equalize image brightness.The fusion weight coefficient is calculated based on the dark channel prior image,and weighted fusion of the three images and detail enhancement are conducted to obtain the final enhanced image.The experimental results show that the proposed algorithm can effectively remove color distortion,and the enhanced image presents high contrast and clearer details.