Recent Advances in Underwater Image Processing

In the last several decades, there has been great interest in underwater images. This could be related not only to the wide diffusion of low-cost waterproof digital cameras that have enriched personal photo galleries, but also to the analysis and monitoring of sea environments through remotely operated and autonomous underwater vehicles. These two different target images (personal and monitoring images) are affected by several distortions typical of underwater environments (color casting, blur, poor contrast and visibility, noise). While many different correction methods exist in the literature, underwater image enhancement and restoration is still an open issue. In the last several years, machine and deep learning methods have been applied to this particular set of images. However, the cardinality of the training data and the availability of ground truth databases pose the major challenges. Finally, to quantify the performance of the image processing methods, underwater image quality assessment is of great importance. One crucial point is how to assess image quality in the case of underwater images. Many different databases exist in the literature, but few of them have been explicitly built to assess the quality of underwater images. In general, this is mainly done manually (by visual inspection), and a proper database is still lacking. In this Special Issue we focus on the recent advancements achieved to improve both kinds of images (personal and monitoring). In particular, we aim to address how these methods can benefit from machine and deep learning algorithms.

Dr. Francesca Gasparini
Dr. Silvia Corchs
Dr. Aurora Saibene
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Signals is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• underwater image enhancement and restoration
• machine and deep learning applied to underwater images
• image quality assessment
• no-reference metrics
• underwater imaging