Image enhancement using a fusion framework of histogram equalization and laplacian pyramid

Abstract

The image enhancement methods based on histogram equalization (HE) often fail to improve local information and sometimes have the fatal flaw of over-enhancement when a quantum jump occurs in the cumulative distribution function of the histogram. To overcome these shortcomings, we propose an image enhancement method based on a modified Laplacian pyramid framework that decomposes an image into band-pass images to improve both the global contrast and local information. For the global contrast, a novel robust HE is proposed to provide a well-balanced mapping function which effectively suppresses the quantum jump. For the local information, noise-reduced and adaptively gained high-pass images are applied to the resultant image. In qualitative and quantitative comparisons through experimental results, the proposed method shows natural and robust image quality and suitability for video sequences, achieving generally higher performance when compared to existing methods.