Gabor滤波器二维卷积模板的获取方法  

Scheme for Designing the 2-D Convolution Mask of Gabor Filter

作　　者：韩润萍[1] 孙苏榕[1] 姜玲[1] 

机构地区：[1]北京市朝阳区和平街北口北京服装学院工业设计与信息工程学院,北京100029

出　　处：《微计算机信息》2007年第02X期241-242,305,共3页Control & Automation

基　　金：北京市教育委员会科技发展计划面上项目基金编号:KM200510012002

摘　　要：本文给出了直接从频域构造Gabor滤波器二维空域卷积模板的计算方法,回避了在空间域对Gabor滤波器冲激响应函数抽样以获取卷积模板所遇到的采样频率的选择问题。该方法首先对Gabor滤波器冲激响应函数的傅立叶变换进行离散化来获得其离散傅立叶变换,然后采用模板的离散傅立叶变换与滤波器的离散傅立叶变换差之模平方和最小的原则来确定模板数据。织物疵点检测实验验证了该方法的正确性和有效性,该方法可应用于应用Gabor滤波器的场合。This paper presents the scheme for designing the 2-D convolution mask of Gabor filter in the frequency domain, This scheme avoids the problem of choosing the sampling frequency in the spatial domain, or the sampling frequency must be determined when the mask is obtained by means of sanzpling the Gabor function, the impulse response of the Gabor filter. In this scheme, the discrete Fourier transform of the Gabor function should be acquired through discretizing the Fourier transform of the Gabor function. The convolution mask of Gabor filter can be derived by minimizing the sums of the squares of the complex magnitudes of deviation between its discrete Fourier transform and the Gabor function＇s. The efficacy of the scheme has been tested by its applications in textile defect detection. The scheme for the designing 2-D Gabor filter convolution mask proposed bv this paper can be used in many fields where Gabor filters are applied.

关 键 词：GABOR滤波器 卷积模板 DFT 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]