利用Gabor滤波分块特征对SAR目标识别

SAR Target Recognition Using Gabor Filter and Sub-block Feature

提出了用Gabor滤波分块统计特征对SAR图像目标进行识别的方法。该方法首先提取预处理后SAR目标图像的低频子带图像,用Gabor滤波器对该子带图像进行滤波,对滤波后各子带图像进行分块,提取所有分块的统计特征作为目标识别特征,最后用支持向量机对该特征进行分类完成目标识别。使用MSTAR数据库中3类SAR目标数据对该方法进行目标识别验证,平均识别率达到93.85%。

A method for SAR target recognition using Gabor filter and sub-block statistical feature is presented in the paper. The low frequency sub-band image extracted from the pre-processed BAR image is filtered by Gabor filter. The each filtered sub-band image is divided into different sub-blocks and the statistical features derived from every sub-block of all filtered sub- band images are regarded as the target recognition feature, which can be used to recognize the targets with SVM. The proposed method is tested and validated on MSTAR dataset for 3-type SAR target recognition, and the average recognition rate is up to 93.85 %.