Analysis of PC number selection in SAR ATR

作者：Wang Ying^*; Han Ping; Wu Renbiao

来源：1st Asian and Pacific Conference on Synthetic Aperture Radar Proceedings, 2007-11-05 to 2007-11-09.

The effect of PC (Principal Component) number upon SAR ATR (Synthetic Aperture Radar Automatic Target Recognition) performance based on PCA (Principal Component Analysis) is analyzed. First, PCA features are extracted with different PC number, and then SVM is used to class. Experimental results based on MSTAR data sets show that the performance is optimized when the accumulative contribution rate of the selected PC is 70%. Compared with the common selected method of PC number, the new selection method improves recognition performance and also reduces computational complexity.

• 出版日期2007
• 单位中国民航大学