X射线头影图象的自适应卡尔曼滤波方法研究

Research on adaptive Kalman filtering of cephalometric image

以口腔医学中Ｘ射线头影图象为背景，提出了一种基于输出相关法的有色噪声卡尔曼滤波方法，用来解决图象中有色观测噪声的滤波问题。该方法不增加滤波器的维数，而是改变系统的观测方程，使等效观测方程的测量噪声变为白噪声，再利用卡尔曼滤波方法进行滤波，大大降低了计算的复杂性。而且该方法不需要事先知道观测噪声的方差，从而弥补了传统卡尔曼滤波方法的不足，更加符合实际情况的需要。实验表明，用该方法对Ｘ射线头影图象进行处理后，可使图象的质量得到明显的改善。

In the view of the drawbacks of the coventional Kalman filtering, a kind of adptive Kalman filtering method of color noise based on correlative method of the system output is proposed to solve the cephalometric images of stomatology. This method builds the Kalman filtering model of color noise by adopting the equivalent observable equation, in order to avoid complicated computation and the expansion of the filter dimension. Also, it is unnecessary to know the variance of measurement noise beforehand so that it is closer to actual situation. Results of several experiments are presented to demonstrate the feasibility and good performance of this method.