Image Enhancement using Sorted Histogram Specification and POCS Postprocessing

An image enhancement algorithm based on the sorted histogram equalization (SHE) and specification (SHS) is proposed in this work. Although SHE and SHS can generate an arbitrary output histogram exactly, they yield false contour artifacts and amplify noises in many cases. To reduce these artifacts, we propose a postprocessing scheme using the projection onto convex sets (POCS) theory. Specifically, the proposed algorithm iteratively processes the output images of SHE and SHS using the low-pass, boundary and dithering conditions. Simulation results demonstrate that the proposed algorithm provides an excellent image quality, by improving the contrast while reducing undesired artifacts.