基于第二代Curvelet变换的低对比度图像增强  

Low contrast image enhancement based on second generation curvelet transform

作　　者：倪雪[1] 李庆武[1] 陈小刚[1] 

机构地区：[1]河海大学计算机及信息工程学院,江苏常州213022

出　　处：《计算机工程与应用》2008年第17期188-190,共3页Computer Engineering and Applications

基　　金：江苏省社会发展科技项目 the Societal Development Research Project of Jiangsu Province; China under Grant No.BS2007058) ;河海大学科技创新基金(No.06B002-02);常州市国家高新区科技项目(No.XE120060408)

摘　　要：针对传统图像增强方法用于低对比度图像时,存在对噪声敏感、局部过增强等问题,提出了一种基于第二代Curvelet变换的增强方法。将图像进行多尺度多方向的Curvelet变换;引入分段非线性函数的思想,调整低频子带系数,提高图像整体的对比度;对各尺度的高频子带系数进行非线性加权,增强图像细节,并进行阈值降噪。实验表明,该方法优于常用的空间域直方图均衡化和小波域图像增强法,能有效地提高图像的对比度、降低噪声,并且较好地保留边缘信息,具有良好的视觉效果。A novel low contrast image enhancement approach based on the second generation curvelet is proposed.h overcomes the shortcomings of conventional methods,such as sensitively to noise and local over-enhancement.Firstly,the source image is decomposed by Curvelet transform.Then a kind of nonlinear enhancing function is applied to enhance the image＇s global contrast in the low ~equency subbands,and combining threshold denoising method with non-linear gain method to reduce the noise and enhance the details of image at each scale in the high frequency subbands.Finally,the enhanced coefficients are reconstructed to obtain enhanced image.Experimental results show that the proposed approach is superior to both histogram equalization and wavelet based contrast enhancement,it can preserve image edges and reduce the noise while enhancing contrast of the image,and also has good visual effect.

关 键 词：CURVELET变换 小波变换 低对比度图像 图像增强 非线性增强函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]