• SUNILRAJ I
• Santhakumar H B
• Sowndhariya K

In this study, a deep convolutional neural network technique is suggested for denoising and recreating underwater photos. To understand the intricate mapping between the noisy and clean images, the suggested method makes use of a deep CNN with several layers. A sizable collection of underwater photos with various types and amounts of noise is used to train the network. The results show that the modern techniques are out performed by the suggested strategy in terms of both subjective visual quality and objective metrics like peak signal-to-noise ratio (PSNR) and structural similarity index. The proposed method's denoising and reconstruction performance is evaluated on several benchmark datasets. Traditional techniques for deblurring underwater photographs can include drawbacks including lost features and blurring. In this paper, we suggest a convolutional neural network- based deep learning method for denoising underwater images. By using a sizable dataset of paired noisy and clean images, the suggested CNN is intended to learn the mapping between noisy and clean underwater images. On a number of benchmark datasets, the proposed CNN's denoising performance is assessed, and the findings show appreciable gains in image quality metrics like PSNR and SSIM.

Keywords—Deep Neural Network (DNN), Machine Learning, Convolutional Neural Network (CNN), Image Reconstruction, Denoising, , Image processing.

"Deep convolutional neural network denoising underwater image reconstruction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.h1-h7, April-2023, Available :http://www.jetir.org/papers/JETIR2304701.pdf

"Deep convolutional neural network denoising underwater image reconstruction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. pph1-h7, April-2023, Available at : http://www.jetir.org/papers/JETIR2304701.pdf