Palmprint identification based on fusion of PCA and DT-CWT features

Biometric identification is more secure compared to the existing traditional ways of identifying a person. In this paper, we propose Palmprint Identification based on Fusion of PCA and DT-CWT Features (PIFPD). The palmprint is preprocessed to obtain Region Of Interest (ROI) to generate features. The features are fused using log multiplication to derive final feature set. The features of test palmprint are compared with database using Euclidian Distance (ED), Random Forest (RF) and Support Vector Machine (SVM). It is observed that the performance of feature fusion by log multiplication is better compared to feature fusion by concatenation and individual PCA and DT-CWT.