Bantupalli Jaisuraj, Kachapilly Amal John, Roy Sanjukta, L K Pavithra
School of Electronics Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, India.
School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, India.
PeerJ Comput Sci. 2024 Nov 29;10:e2392. doi: 10.7717/peerj-cs.2392. eCollection 2024.
Underwater images hold immense value for various fields, including marine biology research, underwater infrastructure inspection, and exploration activities. However, capturing high-quality images underwater proves challenging due to light absorption and scattering leading to color distortion, blue green hues. Additionally, these phenomena decrease contrast and visibility, hindering the ability to extract valuable information. Existing image enhancement methods often struggle to achieve accurate color correction while preserving crucial image details. This article proposes a novel deep learning-based approach for underwater image enhancement that leverages the power of autoencoders. Specifically, a convolutional autoencoder is trained to learn a mapping from the distorted colors present in underwater images to their true, color-corrected counterparts. The proposed model is trained and tested using the Enhancing Underwater Visual Perception (EUVP) and Underwater Image Enhancement Benchmark (UIEB) datasets. The performance of the model is evaluated and compared with various traditional and deep learning based image enhancement techniques using the quality measures structural similarity index (SSIM), peak signal-to-noise ratio (PSNR) and mean squared error (MSE). This research aims to address the critical limitations of current techniques by offering a superior method for underwater image enhancement by improving color fidelity and better information extraction capabilities for various applications. Our proposed color correction model based on encoder decoder network achieves higher SSIM and PSNR values.
水下图像在包括海洋生物学研究、水下基础设施检查和勘探活动等各个领域都具有巨大价值。然而，由于光吸收和散射导致颜色失真，呈现蓝绿色调，在水下拍摄高质量图像具有挑战性。此外，这些现象会降低对比度和能见度，阻碍提取有价值信息的能力。现有的图像增强方法在保留关键图像细节的同时，往往难以实现准确的颜色校正。本文提出了一种基于深度学习的新型水下图像增强方法，该方法利用了自动编码器的强大功能。具体而言，训练一个卷积自动编码器，以学习从水下图像中存在的失真颜色到其真实的、颜色校正后的对应颜色的映射。使用增强水下视觉感知（EUVP）和水下图像增强基准（UIEB）数据集对所提出的模型进行训练和测试。使用质量度量结构相似性指数（SSIM）、峰值信噪比（PSNR）和均方误差（MSE）对模型的性能进行评估，并与各种传统的和基于深度学习的图像增强技术进行比较。本研究旨在通过提供一种卓越的水下图像增强方法来解决当前技术的关键局限性，该方法通过提高颜色保真度和为各种应用提供更好的信息提取能力。我们提出的基于编码器-解码器网络的颜色校正模型实现了更高的SSIM和PSNR值。
