一种基于à Trous算法的水下图像增强算法

An underwater image enhancement algorithm based on à Trous algorithm

针对水下图像的对比度低,噪声大问题,提出一种基于à Trous算法水下图像增强算法。该算法一方面利用直方图均衡,提高水下图像整体对比度;另一方面根据à Trous小波变换的抽取过程允许在不丢失高通细节(如空间和纹理)的空间连续下完成在空间频域上将图像分解在几乎脱节的带通信道上,有效避免由于非线性变换引起的视觉形变;再是模糊对比度增强图像的纹理和边缘信息,从局部增大图像对比度。与当前一些典型的增强方法相比,实验结果表明本文提出的算法的几种客观评价指标明显优于其他算法,能有效提升水下图像的对比度,抑制伪吉布斯现象,而且图像视觉效果也有明显改善。

For underwater images with low contrast,noise is large problem,proposed a new enhancement algorithm,à Trous algorithm based on underwater image.On the one hand,the use of histogram equalization,improve the overall contrast of image under water;on the other hand,according to the extraction process ofàTrous wavelet transform allows without loss of high details(such as space and texture space)under continuous space frequency domain image decomposition in a communication channel almost disjointed,effectively avoid the deformation caused by visual nonlinear transformation;then fuzzy contrast enhancement of image edge and texture information,from the local increase image contrast,so as to obtain high quality of underwater images.With some typical enhancement methods,experimental results show that the proposed algorithm is superior to other kinds of objective evaluation algorithm,can effectively enhance the underwater image contrast,and the image visual effect is significantly improved.