FEATURE EXTRACTION FROM FUSION OF IRIS AND PALMPRINT BIOMETRIC IMAGES FOR RECOGNITION

This paper presents fusion of two biometric traits,i.e.,iris and palm print,at feature level fusion that combines the information from iris and palm print biometric which can achieve better performance,which may not be possible using a single biometric technology. The features are extracted from the pre - processed images of iris and palm print. This system extracts Gabor texture from the pre - processed iris and palm print images. The feature vectors attained from different methods are in different sizes and t he features from equivalent image may be correlated,hence wavelet - based fusion technique is used to fuse both images. Finally the feature vector is matched with database template using Euclidean distance formula.The system is authenticated for their accuracy on Poly U palm print database fused with IITK iris database of 125 users. The experimental results demonstrated that the proposed multimodal biometric system achieves recognition accuracy of 99.2% and with false rejection rate (FRR) of 1.6% and false acceptance rate (FAR) of 6.3% https://www.ijiert.org/paper-details?paper_id=14083