PROJECT TITLE :

Generalization of the Dark Channel Prior for Single Image Restoration - 2018

ABSTRACT:

Pictures degraded by lightweight scattering and absorption, such as hazy, sandstorm, and underwater pictures, often suffer color distortion and low contrast because of sunshine traveling through turbid media. In order to enhance and restore such images, we 1st estimate ambient light-weight using the depth-dependent color amendment. Then, via calculating the difference between the observed intensity and therefore the ambient light, which we tend to call the scene ambient light-weight differential, scene transmission will be estimated. Additionally, adaptive color correction is incorporated into the image formation model (IFM) for removing color casts while restoring contrast. Experimental results on various degraded images demonstrate the new methodology outperforms alternative IFM-primarily based strategies subjectively and objectively. Our approach can be interpreted as a generalization of the common dark channel previous (DCP) approach to Image Restoration, and our technique reduces to several DCP variants for different special cases of ambient lighting and turbid medium conditions.