Underwater Image Enhancement Using Gaussian Pyramid, Laplacian Pyramid and Contrast Limited Adaptive Histogram Equalization
R. Kurinjimalar, J. Pradeep, M. Harikrishnan · 2024
Underwater imaging is essential for capturing submerged environments and it faces significant challenges due to light attenuation, water turbidity and color distortion. This paper presents a novel technique to enlighten underwater image quality through a combination of multiscale image processing techniques like Gaussian and Laplacian pyramids, combined with Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance underwater image. In this paper, five different datasets namely, UIEB, EUVP, RUIE, USR and U45 datasets are used to representing various underwater environments and conditions. Four filtering techniques are employed to sharpen images and the resulting enhancements are showcased. From the result, it is found that the parameters including PSNR, UISM, UICM, PCQI and UIQM reach their maximum value for Laplacian of Gaussian method. Conversely, the gamma correction technique exhibits better performance, particularly in terms of UCIQE and CCQ metrics. It is clear from the suggested method that is applied to the UIEB Real World Underwater Datasets various parameter values are evaluated. The PCQI value is 0.0119, the UIQM value is 0.9998, and the UCIQE value is 30.455, according to the results. It shown in comparison to the other approaches that have been proposed earlier, the UCIQE value is improvised. The proposed method offers a superior solution for enhancing underwater images.