06-01-2011, 04:45 PM
Submitted by: B.N.Ambedkar 09691D3801 M.Tech(D.E.C.S).
Abstract:-
In this project, we present the adaptive bilateral filter (ABF) for automation of natural document images for sharpness enhancement. The ABF sharpness images by increasing the enhancement that is fundamentally different from the un-sharp mask (USM).This approach to sharpness enhancement that is fundamentally different from previous slope restoration also differs significantly from previous slope restoration algorithms in a view that the ABF does not involve detection of edges or their orientation, nor does extract edge profiles. In ABF the edge slope is enhanced by transforming the histogram through a range filter with adaptive offset and width. The ABF is able to smoothen the noise, while enhancing edges and textures in Image. The parameters of ABF are optimized with a training procedure.ABF restores images that are significantly sharper than those restored by the bilateral filter. Compared with USM based sharpening method with optimal un-sharp mask (OUM), ABF restores edges that are sharp as those rendered by slope of the edges without produsing overshoot or undershoot. It is an approach to sharpness the OUM, without the halo artifacts that appear in the OUM restored image. In terms of noise removal, ABF is proposed to outperform the bilateral filter and OUM restored image. In terms of noise removal, ABF is proposed to outperform the bilateral filter and OUM. Evaluation of ABF is carried out in this Work.
