Enhancing Fixed Size Palmprint Region of Interest (ROI) Extraction Algorithm for Personal Identification

Abstract

Identification and verification are the fundamental process in biometrics recognition system. Research indicates that palmprint, as one of the biometric recognitions system is commonly used for human identification. It is because there are many features and information contained inside the palmprint that can be used in the identification process. However, only a small region of the palmprint can be extracted using the existing palmprint region of interest (ROI) extraction algorithms. This has become a problem for identification systems due to negligible and loss of important features which are located outside the ROI. Hence, it is a necessity to improve the palmprint ROI extraction algorithm whereby bigger palmprint ROI can be extracted using this algorithm. Therefore, a larger fixed size extraction algorithm for palmprint ROI is proposed where the extraction region is larger so that more important identification features can be captured inside these ROIs. The performance between proposed and existing extraction algorithms are tested based on two characteristics which are the palmprint ROI extraction area and the comparison of feature creases extracted in a palmprint ROI. The results show that 300x300 fixed size ROI is able to capture 13 out of 14 creases attributes for palmprint identification. This implies that the proposed extraction algorithm shows a promising method of extraction as compared to the existing algorithms.