CNN based color balancing and denoising technique for underwater images: CNN-CBDT

Abstract

Underwater image deteriorates due to the scattering effect of light in the water. The challenging factor in underwater image analysis is the blurring of the image and color distortion. Various techniques were explored to offer solutions for underwater image restoration. But, still, it has some regression exists in these techniques. This proposal introduces the deep CNN-based color balancing and denoising technique (CNN-CBDT) to enhance underwater images. One of the advantages of underwater characteristics is color, mostly green and blue. Due to its low color contrast, the image exists in fuzzy nature. CNN-based CBDT restores the image with the help ReLU unit in the CNN. Lastly, the suggested method's cutting-edge performance is validated by comparing experimental findings to GLNet, Histeq, and ACE algorithms in conditions of structural similarity (SSIM), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), UCIQE, and UIQM. The suggested approach eliminates the impact of underwater elements, enhancing the color of the picture. It enhances PSNR by 17% having the highest value of 19.580 and SSIM by 15% having a value of 0.952. To make it applicable to real robots, the computation speed is calculated. As a result, the proposed method achieved a computation speed of 9.868 frames per second.