Open AccessEnhancement of Individuality Representation for Multi-Biometric Identification
Author(s) -
Wong Yee Leng,
Siti Mariyam Shamsuddin,
Sarina Sulaiman
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/884/1/012061
Subject(s) - biometrics , normalization (sociology) , computer science , identification (biology) , artificial intelligence , pattern recognition (psychology) , fingerprint (computing) , iris recognition , feature (linguistics) , feature extraction , forensic identification , representation (politics) , geography , linguistics , philosophy , botany , archaeology , sociology , politics , anthropology , political science , law , biology
Personal identification is one of the areas in pattern recognition that has created a center of attention by many researchers to work in. Recently, its focal point is in forensic investigation and biometric identification as such the physical (i.e., iris, fingerprint) and behavioural (i.e., signature) style can be used as biometric features for authenticating an individual. In this study, an improved approach of presenting biometric features of true individual from multi-form of biometric images is presented. The discriminability of the features is proposed by discretizing the extracted features of each person using improved Biometric Feature Discretization (BFD). BFD is introduced for features perseverance to obtain better individual representations and discriminations without the use of normalization. Our experiments have revealed that by using the proposed improved BFD in Multi-Biometric System, the individual identification is significantly increased with an average identification rate of 98%.