一种实用的Gabor滤波器组参数设置方法

A Practical Design for Parameters of Gaobr Filters

Gabor滤波器的参数设置是Gabor特征提取过程中的一个重要问题。文中针对现有方法(实验法和优化法)的优缺点,提出一种实用的Gaobr滤波器组参数设置方法,该方法根据Gabor特征与滤波器方向参数之间具有垂直关系的性质,人为确定方向参数。在每个特定方向,以滤波器的频率带宽参数为指导,基于Fisher准则,进行最佳单Gabor滤波器的设计。确定的滤波器组在性能上是接近最优的,同时算法实现简单,具有较好的实用性和数据相关的特点。在车辆检测和车型识别两类实验中验证了文中方法的有效性和可行性。

During the course of Gabor filters-based feature extraction, the design for parameters of filters is important. Experiment-based and optimization-based methods are two popular ways in this domain. However, the parameters are not precise in the former and the algorithm is too complex in the latter. To avoid these defects, a more practical one is given. The main idea is to set the orientation parameters manually based on directional characters in Gabor features, then at each orientation with the help of the bandwidth parameters to search the optimal single Gabor filter on the basis of Fisher rule. The parameters of Gabor filters are close to optimization, and the algorithm is simple and data dependent as well. The experimental data on vehicle detection and vehicle classification show that this method is available and efficient.