蓝善营, 陆安山. 基于NSCT的水下图像清晰化算法[J]. 微电子学与计算机, 2021, 38(3): 56-60.
引用本文: 蓝善营, 陆安山. 基于NSCT的水下图像清晰化算法[J]. 微电子学与计算机, 2021, 38(3): 56-60.
LAN Shan-ying, LU An-shan. Underwater image visibility improving algorithm based on NSCT[J]. Microelectronics & Computer, 2021, 38(3): 56-60.
Citation: LAN Shan-ying, LU An-shan. Underwater image visibility improving algorithm based on NSCT[J]. Microelectronics & Computer, 2021, 38(3): 56-60.

基于NSCT的水下图像清晰化算法

Underwater image visibility improving algorithm based on NSCT

  • 摘要: 针对水下环境采集到图像质量发生严重退化的问题,提出了基于非下采样轮廓波变换(Non-subsample Contourlet Transform, NSCT)的水下图像清晰化算法.先对图像预处理,补偿红色通道,再进行白平衡和锐化,把白平衡图像和锐化图像作为输入,进行NSCT分解.对于低频分量,提出了一种区域方差与加权拉普拉斯能量和的融合方法;采用了改进的引导滤波对高频分量进行处理;最后进行逆NSCT变换和颜色校正,获得清晰的水下图像.实验结果表明,该算法纠正了水下图像色偏,提升图像对比度,突出细节信息,显著提高了水下图像的质量.

     

    Abstract: A non-subsample Contourlet Transformalgorithm for underwater image sharpening was proposed to reduce the degradation of underwater image quality.First, the image is preprocessed, the red channel is compensated, and then the white balance and sharpening are carried out. The white balance and sharpening images are taken as the input for NSCT decomposition. For low frequency components, a fusion method of regional variance and weighted Laplace energy sum is proposed. An improved guided filter is used to process the high frequency components. Finally, inverse NSCT transform and color correction are carried out to obtain clear underwater images. Experimental results show that the algorithm corrects the color distortion, improves the image contrast, highlights the details, and significantly improves the quality of the underwater images.

     

/

返回文章
返回