图像边缘提取的自适应Volterra滤波器设计

The Adaptive Design of Volterra Filters for Edge Detection of Images

Ｖｏｌｔｅｒａ滤波是研究信号高阶统计冗余性的一种有效途径．我们提出了一种用于提取图像边缘的自适应二次Ｖｏｌｔｅｒａ滤波器设计方法．这种滤波器是推广型Ｔｅａｇｅｒ基滤子的线性组合，其系数用基于极小化最小均方能量函数的共轭梯度法确定；它兼有局域平均和高通特性，因而可均衡去除噪声和增强图像边缘．文章还给出了计算实例．

The Volterra operations are an effective way for the explorations of higher order statistical redundancies of signals.We present a design method for adaptive quadratic Volterra filters with application to edge detection of images.The filter is expressed as a linear combination of generalized Teager basis filters.The expression coefficients are determined by minimizing the least mean square (LMS).This filter,like a local mean weighted highpass filter,can balance the reducing noise and enhancing feature.