基于Contourlet变换和形态学的图像增强方法  

Image Enhancement Based on the Contourlet Transform and Mathematical Morphology

作　　者：向静波[1,2] 苏秀琴[1] 陆陶[1,2] 

机构地区：[1]中国科学院西安光学精密机械研究所,西安710119 [2]中国科学院研究生院,北京100049

出　　处：《光子学报》2009年第1期224-227,共4页Acta Photonica Sinica

摘　　要：传统的图像增强算法在增强图像时,增大噪音,同时丢失细节.针对该问题,结合Contourlet变换中相关系数理论,提出了基于Contourlet变换和数学形态学的图像增强新算法.首先,对图像进行Contourlet变换分解,采用数学形态学算子对高频细节部分区分为细节信息和噪音产生的系数,然后,对变换系数采用非线性映射函数进行增强.最后,利用修改后的变换系数进行Contourlet逆变换得到增强后的图像.实验表明,该方法无论是增强效果还是抗噪性能都明显优于传统的图像增强算法.Traditional methods for image enhancement cannot capture the geometric information of images and tend to amplify noise. To overcome the above enhancement issues, a new enhancement algorithm for image was proposed based on the Contourlet transform and mathematical morphology. The new algorithm decomposed image into approximation-coefficients and detail coefficients. Morphological dilation operations was used to distinguish noise form detail information according to dependencies of contourlet coefficients, then nonlinear mapping function was used to modify the contourlet coefficients. And the enhanced image were obtained by contourlet inverse transform. The experiments show that utilizing the proposed algorithm can enhances image detail and the signal to noise ratio.

关 键 词：图像增强 CONTOURLET变换 数学形态学 多尺度几何分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]