基于四元数小波变换HMT模型的图像去噪

Image Denoising Based on HMT Model of Quaternion Wavelet Transform

实小波变换域中的图像去噪会产生伪Gibbs现象,为此,提出一种基于四元数小波变换的隐马尔可夫树模型(Q-HMT),并应用于图像去噪。模型结合四元数小波变换理论与HMT模型,体现小波系数层间的相关性,捕获小波系数邻域的统计特征。实验结果表明,该模型的图像去噪效果在峰值信噪比以及视觉效果上均优于经典的去噪方法。

According to the Gibbs effect of image denoising in real wavelet transform domain,this paper proposes a Hidden Markov Tree（HMT） model based on Quaternion Wavelet Transform（QWT）.The QWT theory and HMT are combined in this model which effective reflect the correlation between wavelet coefficient and capture the neighborhood statistical characteristics of wavelet coefficients.Experimental results show that the model both in Peak Signal to Noise Ratio（PSNR） and in the visual effect are better than many classic denoising method.