Ear Recognition Using KDA/GSVD and SVM
基于KDA／GSVD和支持向量机的人耳识别

Ear recognition is one of important branches of biometrics.We proposed a new ear recognition method which uses KDA/GSVD method to reduce image dimensions and support vector machines as classifier.The experimental results on the USTB-77 ear database show that the new method can overcome the singularity problem of covariance matrices that represent the scatter within and between clusters and perform well in accuracy simultaneously.