基于模板分解与递归式滤波的遥感图像快速Gabor纹理特征提取

Extracting Texture Features from Remotely Sensed Imagery with Fast Gabor Filters Implemented with Kernel Decomposing and Recursive Filtering

设计一种在x、y轴方向上进行2维Gabor滤波器模板分解的可行方法,从而避免模板分解时在倾斜方向上进行重采样所带来的效率、精度损失;接着采用递归方法实现分解后的1维滤波器以进一步提高算法效率。采用高斯滤波对Gabor滤波结果进行校正平滑作为纹理特征输出,并采用k-means算法对其进行聚类以验证方法在提取图像纹理区域时的有效性。和以快速傅里叶变换方式实现的Gabor纹理提取方法进行对比,实验表明,该方法在纹理特征提取上的精度损失很小,但在算法执行效率上则有显著的提高。

A fast remotely sensed image texture feature extracting method is proposed. It firstly decomposesa 2-D Gabor filter along x, y axes into a set of 1-D filters, which avoids the precision and efficiency losing of re-sampling which is necessary when the decomposing is carried out along some inclined orientations of an image plane. Be- sides, a recursive method is implemented to further improve the efficiency of the decomposed 1-D filtering. A Gaussian filter is used to smooth the filtering outputs, which are then subjected to k-means clustering method for textural image segmentation. A comparison between the method and FFT-based Gabor filtering method is carried out. It demonstrates that our method is a feasible and fast way tO extract texture features from remotely sensed imagery, for its higher algorithm efficiency and little precision losing.