基于复小波邻域隐马尔科夫模型的图像去噪

多分辨信号和图像模型可用于捕获图像中平滑和奇异区域的统计结构,但是,基于正交小波变换的模型受到平移变化的影响从而降低了其准确性和实时性.本文将邻域隐马尔科夫模型LCHMM( Local Contextual Hidden Markov Model)扩展到复小波的范围,提出了一种基于复小波的邻域隐马尔科夫模型C-LCHMM( Local Contextual Hidden Markov Model Based On Complex Wavelet),该模型具有近似平移不变性及分辨率高的特点、能够捕获小波系数的邻域的统计特征、且计算复杂度小.仿真试验表明基于复小波邻域隐马尔科夫模型(C-LCHMM)用于图像去噪的效果优于典型的去噪算法.

Image Denoising Using Local Contextual Hidden Markov Model Based on Complex Wavelet

Multiresolution signal and image models aim to capture the statistical structure of smooth and singular regions.Unfortunately,models based on orthogonal wavelet transform suffer from shift-variance,which makes them be less accurate and real-time.In this paper,we extend the local contextual hidden markov model(LCHMM)modeling framework to the complex wavelet transform and proposed a new model,called local contextual markov model based on complex wavelet(C-LCHMM),which features near shift-invariance and improved angular resolution and can exploit the local statistics of wavelet coefficients at a low computational complexity.