Underwater image enhancement is a challenging task and has gained priority in recent years, as the human eye cannot clearly perceive underwater images. We introduce an effective technique to develop the images captured underwater which are degraded due to the medium scattering and absorption. Our proposed method is a single image approach that does not require specialized hardware or knowledge about the structure of the hardware or underwater conditions. We introduce a new underwater image enhancement approach based on multi scale fusion strategy in this paper. In our method, we first obtain the restored image on the base of underwater image model. Then we get the white balance and contrast enhancement image of the restored image respectively. Finally, these two derived inputs are blended by multi scale fusion approach, using saturation and contrast metrics to weight each input. To avoid the sharp weight map transitions that create artifacts in the low frequency of the reconstructed image, multistage fusion strategy is adapted. Experimental results on real world as well as mock underwater images demonstrate that the proposed method is a simplified approach on different underwater scenes and outperforms the existing methods of enhancement.
by Marshall Mathews | Riya Chummar | Sandra | Ms. Sreetha E. S. ""Literature Survey on Underwater Image Enhancement""
Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-3 , April 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30592.pdf
Paper Url :https://www.ijtsrd.com/engineering/computer-engineering/30592/literature-survey-on-underwater-image-enhancement/marshall-mathews
callforpapertechnology, technologyjournal
No comments:
Post a Comment