Journal of Visual Communication and Image Representation (JVCI)
In this paper, we present a novel method to restore the visual quality of images from scenes immersed in participating media, in particular water. Our method builds upon existing physics-based model and estimates the scene radiance by removing the medium interference on light propagation. Our approach requires a single image as input and, by combining a physics-based model for light propagation and a set of quality metrics, reduces the artifacts and degradation imposed by the attenuation, forward scattering, and backscattering effects. We show that the resulting images produced by our technique from underwater images are amenable to be directly used as input to algorithms which do not assume disturbances from the media. Our experiments demonstrate that, as far as visual image quality is concerned, our methodology outperforms both traditional image based restoration approaches and the state-of-the-art methods. Our approach brings advantages regarding descriptor distinctiveness which enables the use of underwater images in legacy non-participating media algorithms such as keypoint detection and description.
We compare the proposed methodology against the following methods:
- Baz Algorithm – Bazeille et al., Automatic underwater image pre-preprocessing, CMM 2006.
- DCP – He et al., Single image haze removal using dark channel prior, IEEE Trans. Patt. Ana. and Mach. Intel. 2011.
- UDCP – Drews et al., Underwater depth estimation and image restoration based on single images, IEEE Comp. Graph. App. 2016.
- Tarel Algorithm – Tarel and Hautière, Fast visibility restoration from a single color or gray level image, ICCV 2009.
- Fusion Maps – Ancuti et al., Multi-scale underwater descattering, ICPR 2016.
Wagner Ferreira de BarrosProfessor IFMG
Walysson Vital BarbosaMSc Student