非均匀光照条件下的水下图像增强算法

Underwater image enhancement algorithm of uneven illumination

自然水域非均匀光照环境中,针对图像存在模糊、对比度低、颜色失真等退化现象,提出一种视觉显著性分割和Retinex算法相结合的水下图像增强方法。首先,依据图像的亮度、色度和方向特征得到图像显著图,进而分割出前景区域和背景区域;然后,基于Retinex算法分别对两区域增强处理,并对背景区域进行二次增强;最后,采用泊松融合算法得到两区域增强后的合成图像。实验结果表明,提出的算法提高了水下非均匀光照条件下的图像清晰度,与其他算法相比,具有更好的性能。

In view of the blurring,low contrast and color distortion of images in the natural water environment with uneven illumination,an underwater image enhancement method was proposed by combining visual saliency segmentation and Retinex algorithm.Firstly,the image saliency map obtained in accordance with its brightness,chromaticity and directional characteristics was segmented into the foreground area and the background area.Secondly,the two areas are enhanced based on Retinex algorithm and the background area was secondly enhanced.Finally,the enhanced image was fused by using the Poisson fusion algorithm.The experimental results show that the proposed algorithm effectively improves the clarity of underwater images and has better performance than other algorithms.