快速小波域隐马尔可夫模型的图像去噪

Fast image de-noising based on wavelet using hidden Markov models

在分析小波系数的指数衰减性和延续性的基础上,提出了一种模型参数初始化的方法.MATLAB仿真实验结果表明,该方法给出了合理的模型参数初值,在有效缩短训练时间的同时能获得较理想的去噪结果.

Expected maximization algorithm being used to training model in wavelet-based HMM. Always leads to slow down the convergence rate. In this paper, the persistence and exponential decay characteristics of wavelet coefficient are analyzed, a model parameter initialization method is proposed. Simulation results indicate that this method provides reasonable initial model value. Better image de-noising results are obtained within shorter time.