Fusion based variational image dehazing - 2017 PROJECT TITLE :Fusion based variational image dehazing - 2017ABSTRACT:We have a tendency to propose a unique image-dehazing technique based on the minimization of two energy functionals and a fusion theme to combine the output of each optimizations. The proposed fusion-based variational image-dehazing (FVID) technique may be a spatially varying image enhancement process that first minimizes a previously proposed variational formulation that maximizes distinction and saturation on the hazy input. The iterates created by this minimization are kept, and a second energy that shrinks faster intensity values of well-contrasted regions is minimized, permitting to come up with a collection of distinction-of-saturation (DiffSat) maps by observing the shrinking rate. The iterates created in the first minimization are then fused with these DiffSat maps to provide a haze-free version of the degraded input. The FVID methodology will not depend on a physical model from that to estimate a depth map, nor it wants a training stage on a database of human-labeled examples. Experimental results on a large set of hazy images demonstrate that FVID higher preserves the image structure on nearby regions that are less affected by fog, and it's successfully compared with other current ways in the task of removing haze degradation from faraway regions. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Image Enhancement Using Morphological Contrast Enhancement For Video Based Image Analysis - 2017 A Robust and Efficient Approach to License Plate Detection - 2017