Enhancing Underwater Images Using Deep Learning with Subjective Image Quality Integration

TL;DR

This paper introduces a deep learning approach that enhances underwater images by incorporating human subjective quality assessments into the training process, leading to improved image clarity and color fidelity.

Contribution

It presents a novel integration of subjective image quality assessments into deep learning models for underwater image enhancement, combining classifier and GAN techniques.

Findings

Significant improvements in PSNR, SSIM, and UIQM metrics.

Enhanced perceived image quality through subjective assessment integration.

Effective use of GANs with quality criteria like color fidelity and sharpness.

Abstract

Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving underwater image quality by integrating human subjective assessments into the training process. To this end, we utilize publicly available datasets containing underwater images labeled by experts as either high or low quality. Our method involves first training a classifier network to distinguish between high- and low-quality images. Subsequently, generative adversarial networks (GANs) are trained using various enhancement criteria to refine the low-quality images. The performance of the GAN models is evaluated using quantitative metrics such as PSNR, SSIM, and UIQM, as well as through qualitative analysis. Results demonstrate that the proposed model -- particularly when incorporating criteria such as color fidelity and image sharpness -- achieves substantial improvements in both perceived and measured image quality.