Abstract—The water medium is not particularly conducive for the acquisition of underwater images. This is due to its nature; with the presence of small floating particles in the water medium, causing the scattering of light and attenuation of wavelength, as well as the loss of light, especially in deep water environment. These issues make the captured underwater images less informative, requiring the use of image processing methods to make underwater images more meaningful. To evaluate and compare the performance of different image processing methods, a proper underwater image dataset with various conditions, is of utmost importance. For this purpose, an underwater image dataset; obtained using GOPRO HERO7 SILVER underwater camera, taken at different conditions of underwater environment, has been developed. This manually curated underwater dataset is referred to as Simulated Water Type Dataset (SWTD), and it is based on different water type. The dataset is also made publicly available, which can be used in evaluating image enhancement and restoration methods. A few selected state-of-the-art image processing methods has also been tested on this dataset for illustration purpose, with results analysed quantitatively and qualitatively.
 

Index Terms—underwater images, image restoration, image enhancement, simulated dataset, Jerlov water types

Cite: Jarina Raihan A, Pg Emeroylariffion Abas, and Liyanage C De Silva, "A Simulated Water Type Dataset (SWTD) Based on Jerlov Water Types for Underwater Image Quality Analysis," Journal of Advances in Information Technology, Vol. 12, No. 4, pp. 334-341, November 2021. doi: 10.12720/jait.12.4.334-341

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.