一种新的基于区域角度搜索的各向异性高通滤波算法

A New Anisotropic High-pass Filtering Algorithm Based on Region Angle Searching

采用梯度方向法估计的边缘方向往往与实际边缘方向存在的较大差距,导致高通滤波的效果降低。在研究了滤波器长轴和边缘方向的夹角对滤波效果影响曲线的基础上,提出了一种新的基于区域角度搜索的各向异性高通滤波算法,以采用梯度方向法估计的边缘方向角为初始值,利用区域搜索寻找实际的边缘方向角,同时获得该搜索步长下最佳的滤波效果。如果严格遵循"滤波器长轴与实际边缘方向重合"时,将得到理想高通滤波效果,实验结果表明,采用本文滤波方案所得到的滤波效果更趋近于理想。

The edge＇ s orientation obtained with the method of gray gradient orientation may be quite different from the real edge＇ s orientation, leading to the deterioration of the high-pass filtering performance. The influences of the angle of the edge＇ s orientation and the filter＇ s long axes on the filtering performance are studied, and a new anisotropic high-pass filtering algorithm based on region angle searching is proposed in this paper. The angle of gradient is taken as an initial angle. The region angle searching algorithm is then employed to calculate the real edge orientation and to obtain the best high-pass filtering performance at the current searching step. We can achieve the ideal filtering performance on the condition that the orientation of the filter＇ s long axes is consistent well with that of the real edges. The experimental result shows that the filtering performance with the new algorithm put forward in the paper is close to the ideal performance.