摘要
在分析contourlet域系数分布特征的基础上提出了一种基于context模型的contourlet域图像去噪算法。算法的关键点在于:基于contourlet变换系数的分布特性,确定合适的去噪门限;利用context模型建立图像contourlet变换后的系数分类模型并根据分类使用不同的门限去噪。实验表明,本方法能较好地去除图像噪声,在提高去噪图像PSNR值和改善主观视觉效果方面都表现出了良好的性能。
This paper presented an image denoising algorithm based on context model by analyzing distribution features of contourlets coefficients. The key of the proposed arithmetic is that through the analysis of CT coefficients distribution characteristics, we chose the appropriate denoising thresholding, adopted the context model to construct CT coefficient＇s classification model, and according to different classification, image noise was removed by using different threshold. The experimental results show that the proposed algorithm can effectively remove the noise in images. The algorithm also demonstrates good performance in enhancing image PSNR and improves the image subjective visual impression.
出处
《计算机科学》
CSCD
北大核心
2012年第3期243-245,共3页
Computer Science
基金
国家自然科学基金(60976020)资助
