PROJECT TITLE :

Weighted Guided Image Filtering - 2015

ABSTRACT:

It's known that local filtering-primarily based edge preserving smoothing techniques suffer from halo artifacts. In this paper, a weighted guided image filter (WGIF) is introduced by incorporating a footing-aware weighting into an existing guided image filter (GIF) to deal with the problem. The WGIF inherits blessings of each global and local smoothing filters in the way that: one) the complexity of the WGIF is O(N) for a picture with N pixels, that is same because the GIF and a couple of) the WGIF can avoid halo artifacts like the prevailing global smoothing filters. The WGIF is applied for single image detail enhancement, single image haze removal, and fusion of differently exposed pictures. Experimental results show that the resultant algorithms turn out pictures with better visual quality and at the identical time halo artifacts will be reduced/avoided from appearing in the ultimate images with negligible increment on running times.