基于颜色校正和多尺度融合的水下图像 增强
首发时间:2019-06-04
摘要:针对水下图像颜色失真、对比度低、以及非均匀光照等问题,提出一种有效的水下图像增强算法。首先,基于白平衡算法对水下退化图像进行处理,并通过伽玛校正解决增强后部分图像区域过亮或过暗的问题,得到颜色校正后的图像;再对白平衡处理后的图像进行自适应对比度拉伸,并通过引导滤波去噪得到高对比度的水下清晰图像;最后将这两幅图像作为融合过程的输入,进行多尺度融合。实验结果表明,本文算法能有效提高水下图像对比度,解决水下图像模糊和光照不均问题,且在无需任何先验信息的条件下,广泛适用于多种水下退化图像,有效提高图像视觉质量。
关键词: 图像处理 水下图像增强 多尺度融合 白平衡 伽玛校正 引导滤波
For information in English, please click here
Underwater image enhancement based on color correction and multi-scale fusion
Abstract: An effective underwater image enhancement algorithm was proposed to solve the problems of color distortion, low contrast and uneven illumination. Firstly, the original image is processed based on the white balance algorithm, and the problem of over-bright or over-dark parts of the enhanced image area is solved by gamma correction, and the color-corrected image is obtained. Next, adaptive contrast stretch was carried out for the image after the white balance processing, and the high contrast underwater image was obtained by guided filtering and denoising. Lastly, these two images are used as the input of the fusion process for multi-scale fusion. Experimental results show that the proposed algorithm can effectively improve the contrast of underwater images, solve the problem of underwater image blurring and uneven illumination, and is widely applicable to a variety of underwater degraded images without any prior information, effectively improving the image visual quality.
Keywords: Image processing Underwater image enhancement Multiscale fusion The white balance Gamma correction Guide the filtering
引用
No.****
动态公开评议
共计0人参与
勘误表
基于颜色校正和多尺度融合的水下图像 增强
评论
全部评论0/1000