Multiscale X-ray image contrast enhancement based on limited adaptive histogram equalization

Abstract

In this paper, a novel image contrast enhancement method, based on multiscale transform and contrast limited adaptive histogram equalization, is proposed for enhancing the X-ray images. Firstly, the Laplacian pyramid based the multiscale transform is adopted to decompose the input image, which can extract the characteristic of multiscale the image. Secondly, the contrast limited adaptive histogram equalization (CLAHE) is used for enhancing the contrast of image. Comparing with the traditional adaptive histogram equalization (AHE) and global histogram equalization, the CLAHE effectively intensifies the image at the same time restrains noise enlarged. In order to make the enhanced image become more smoothing, we adjust the contrast of low frequency coefficients. Finally, the inverse Laplacian pyramid transform is applied to reconstruct image which can obtain the enhanced image. We tested the proposed algorithm on medical X-ray images, and experimental results show that the presented algorithm is effective for contrast enhancement of image. The performance evaluation of the proposed algorithm uses the contrast evaluation criterion for image and information entropy.