Fusion of multiscale gradient domain enhancement and gamma correction for underwater image/video enhancement and restoration

•To enhance degraded underwater images and video, color correction, gamma correction, gradient-domain enhancement have been employed.•The gamma correction is used to enhance the base layer while the S-shape function is utilized to enhance detail layers.•To validate the proposed method, the PSNR, SSIM, EME, DE, UIQM, and UCIQE, have been evaluated on the UIEB and U45 datasets.•The proposed method and existing state-of-the-art methods are tested on a DRUVA dataset.•The efficiency of proposed method tested on fog image and low illumination images. Underwater images and video often suffer from poor visibility and color cast because light gets scattered and absorbed in water. To solve this problem, a novel method based on the fusion of multiscale gradient-domain enhancement and gamma correction is proposed for underwater images and video enhancement. Firstly, a white balance is used for color correction to the input underwater image and video. secondly, the color corrected underwater RGB images are converted to YCbCr color space. The Y-component of the image is decomposed into the base layer and detail layers using a Weighted Least Squares (WLS) filter. The base layer is enhanced by using gamma correction and detail layers are enhanced using the S-shape function in the gradient domain. The enhanced base layer and detail layers are fused. Finally, the fused image combined with Cb and Cr-component of YCbCr color space to obtained enhanced image. The proposed method has been implemented on the Underwater Image Enhancement Benchmark (UIEB) dataset, Underwater-45 (U45) dataset, and Dataset Real-world Underwater Video of Artifacts (DRUVA) based on the Peak Signal-to-Noise Ratio (PSNR), Structure Similarity Index Measure (SSIM), Measure of Enhancement (EME), Discrete Entropy (DE), Underwater Image Quality Measure (UIQM), and Underwater Color Image Quality Evaluation (UCIQE). To verify the efficacy of the proposed method, a qualitative and quantitative comparison has been conducted on the UIEB, U45, and DRUVA datasets. The result demonstrates that the proposed method outperforms the state-of-the-art method, in terms of PSNR, SSIM, EME, UIQM, and UCIQE parameters. Furthermore, the efficiency of proposed method tested on fog image and low illumination images.