Local correction with global constraint for image enhancement

This paper presents a method to improve the image contrast adaptively with account of both local and global image context. Firstly, the image is analyzed to find the region containing meaningful contents with good contrast and the region containing meaningful contents but with poor contrast. The analysis is based on the different responses from two edge detectors: the Canny and the zero-crossing detector. Then statistics of the gradient field in the former region is utilized to correct the gradient field in the latter region. Reconstruction of the contents in the latter region is accomplished through solving a Poisson equation with Dirichlet boundary conditions. Throughout the process, objects with poor visibility are automatically detected and adaptively enhanced without sacrifice of the contrast of image contents that are properly illuminated. Experiments show the advantages of the proposed method over the conventional contrast enhancement methods.