Graph signal processing based underwater image enhancement techniques

Abstract

This paper presents two new methods based on graph signal processing (GSP) techniques to enhance underwater images. The proposed schemes utilize the graph Fourier transform (GFT) and graph wavelet filterbanks in place of the conventional Fourier and wavelet transforms. Initially, the raw images are represented on a chosen graph structure, and then the root-filtering is applied in the GFT and graph wavelet transform (GWT) domains in the present work. It is observed that the root-filtering parameter plays a crucial role in the image enhancement process. The root filtering method highlights the high frequency terms, which pertain to edges and textural elements with smaller amplitudes, while de-emphasizing the higher magnitude frequency components. As a result, the high frequency components are accentuated in contrast to the lower frequencies, resulting in a sharper and more visually appealing image. The simulation results of the proposed techniques are compared with the existing enhancement methods. It is shown that the proposed approaches offer more improvement in the enhanced image quality than the current methods considered in this paper. It is also seen that the root-filtering parameter in the range of 0.75 to 0.95 and Mexican hat wavelet in the proposed graph wavelet filterbank based approach with N = 5 improve the quality of enhancement of underwater images.