Underwater image de-noising algorithm based on Nonsubsampled Contourlet Transform and Total Variation

Abstract

According to the characteristics of underwater image, this paper proposed a underwater image de-noising algorithm based on Nonsubsampled Contourlet Transform (NSCT) and Adaptive Total Variation (ATV) de-noising model. In our method, the underwater image is decomposed into low frequency part and high frequency part. ATV de-noising model is applied to high frequency part. Experimental results show that the method can not only eliminate the noise, but also retain edge and texture of the target very well.