
The underwater images (UIM) are rigorously degraded by colour deviations, scattering, and absorption. This can be addressed by enhancing the UIM. Prior knowledge of the degradation model is combined with enhancement methods to achieve superior performance. We have used a hybrid approach that incorporates the White Balancing (WB) technique for colour correction, CLAHE for enhancing contrast, and the Dark Channel Prior (DCP) method to decrease haziness in the image. Firstly, the UIM is colour corrected using WB. CLAHE is applied on a white-balanced image. DCP is also applied on white-balanced images to remove haziness. Finally, CLAHE output and DCP output are fused at a multi-scale by considering different weight maps to obtain the enhanced UIM. The U45, RUIE, and UIEB datasets are used to validate the effectiveness of the devised technique. A comparison of the developed technique with current methods reveals that the developed technique is superior.
Published in Evergreen, Volume 12, Issue 03. Citation formats available via DOI link.
color correction, underwater image, contrast enhancement, image enhancement, life underwater, de-haziness
color correction, underwater image, contrast enhancement, image enhancement, life underwater, de-haziness
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
