An Improved Multi-Scale Image Enhancement Method Based on Retinex Theory

摘要

Medical digital images are usually difficult to identify due to their poor brightness and low contrast. In order to enhance these images, this paper presents an algorithm of digital radiography enhancement based on Multi-scale Retinex. Initially, gray-level grouping is used to improve the contrast of the illumination part of the image instead of histogram equalization. Secondly, nonlinear mapping function is chosen to be the gain function, and local contrast is selected as the parameter of the mapping function. The experimental results show that the proposed method enhances the edge and the detail information, the contrast is significantly improved, and the noise is well suppressed.