摘要
针对实验图像光照不均、对比度低、噪声大等特点,提出一种基于非抽样contourlet变换的图像非线性增强算法.首先对原图进行非抽样contourlet变换,分解为低频和高频子带;然后对低频子图进行自适应直方图处理,以增强像素的对比度,对高频系数采用分层阈值处理和分段非线性变换;最后将其反变换得到增强的图像.仿真实验结果表明:此算法不仅增强效果好,鲁棒性强,而且具有较大的实用价值.
Based on nonsubsampled contourlet transform（NSCT） and experiment image statistical property which contains uneven illumination,low comparison and high noise,an image enhancement method is presented.Firstly the original image is carried on nonsubsampled contourlet to be decomposed into low and high coefficients sub-band.Then the low frequency is carried on adaptive histogram processing to enhance the contrast of pixels.The high frequency coefficients are classified by threshold and carried on non-linear transformation.Finally the enhanced image can be obtained after inverse NSCT.Experimental results show that such method is not only effective and robust,but also practical.
出处
《扬州大学学报（自然科学版）》
CAS
CSCD
北大核心
2011年第4期47-51,共5页
Journal of Yangzhou University：Natural Science Edition
基金
国家自然科学基金资助项目(20299030)
扬州大学自然科学基金资助项目(KK0313090)
