WSEAS Transactions on Signal Processing
Print ISSN: 1790-5052, E-ISSN: 2224-3488
Volume 15, 2019
A Multimodal Authentication for Biometric Verification System Using Palmprints and Fingers
Authors: ,
Abstract: Trusted identification approaches play a critical role in everyday life and daily activities of humans. Hand as a physiological characteristic that has high acceptability and stability that contains several biometrics components has attracted the attention of many scholars so that almost all parts of it are considered as a member of the biometric system. The proposed method in this research is verification by a color image of the palm of the hand and the index, middle, ring and little fingers which is implemented by a new method for extracting texture features on images of 177 individuals from the Hong Kong Polytechnic University Contact- Free 3D / 2D Hand Images Database. The proposed feature extraction method is the use of Turn Counts in each of Gabor’s filters applied in different directions and scales on each of the RGB components of the images individually. Before classification, a binary genetic algorithm is applied to use the best combination of features for each color component. The system performance has been studied in unimodal and multimodal modes using the SVM classification and the best result is obtained based on combining the features of the palm and four fingers with an EER of 0.67 ± 0.13. Also, the effectiveness of this method has been investigated by generalizing the feature extraction method on other databases in this domain.
Search Articles
Pages: 129-141
WSEAS Transactions on Signal Processing, ISSN / E-ISSN: 1790-5052 / 2224-3488, Volume 15, 2019, Art. #16