基于Contourlet的图像PCA去噪方法

提出了一种通过主分量分析(PCA)对Contourlet域中噪声能量的估计来实现去噪的新方法。Contourlet变换是一种结合多分辨率分析和方向性滤波的小波变换,它除了具有一般小波变换的多尺度、时频局域性外,还具有多方向性、各向异性等特征。因此,Contourlet能有效地捕获到自然图像中的轮廓,并对其进行稀疏表示。目前使用的小波去噪方法基本上都是建立在对噪声方差估计的基础上,而在Contourlet变换系数中,通过建立数学模型对噪声方差进行精确的估计是很困难的。算法无需对噪声方差进行估计,更具有实用价值。实验结果显示,与小波软、硬阈值去噪算法和基于小波的图像PCA去噪方法比较,该算法不仅提高了图像的信噪比,而且图像视觉效果也明显改善。

Contourlet image de-noising based on principal component analysis

This paper proposes a new method which utilizes noise energy,instead of its variance,to perform image de-noising based on Principal Component Analysis(PCA) in Contourlet domain.The Contourlet transform is a new extension of the wavelet transform in two dimensions.Its main feature is combining non-separable directional filter with wavelet filter.Most of the existing methods for image de-noising rely on accurate estimation of noise variance.However,the estimation of noise variance is very hard in Contourlet domain.Propose a new method for image de-noising based on the Contourlet transform.Experiments in de-noising the typical image Barbara show that the performance of the proposed method is obviously superior both in vision and in PSNR.