Image Enhancement Algorithm for Fusion of Double-density Dual-tree Complex Wavelet Transform and Multi-scale Retinex
WANG Gaofeng
SHI Zhonglei
TAN Weimeng
LI Si
GAO Tao
Abstract：For the existing problems of bad image recognition and halo,enhancement,and easy loss of details what the classi?cal multi scale Retinex algorithm exerts in low light situations,the paper poses an image enhancement algorithm of fusion of dou?ble-density dual-tree complex wavelet transform and multi-scale Retinex. At first,double-density dual-tree complex wavelet trans?form is conducted for the image to be enhanced,getting the 4 low frequency image components and 32 high-frequency image compo?nent of the original image. The classical multi scale Retinex algorithm is used for each low frequency image component,median fil?tering for each high frequency image component,after the inverse wavelet transform,the enhanced image is obtained finally. With light and shade photos and darker as the data source in low light situations,the subjective evaluation and the objective PSNR,infor?mation entropy is used as the evaluation standard to inspect image enhanced or not. The experimental results demonstrate that the method enhances the image details in low light circumstances,solves the enhancement and halo problem of traditional algorithm.
Keywords：double-density dual-treeRetinexlow lightimage evaluation
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 870-873,934 )