No Detail Found!

INDIVIDUALITY REPRESENTATION USING MULTIMODAL BIOMETRICS WITH ASPECT UNIETED MOMENT INVARIANT FOR IDENTICAL TWINS

Author(s)
BAYAN OMAR MOHAMMED College of Science and Technology, University of Human Development, Sulaimani, KRG, Iraq; UTM Big Data Centre, Ibnu Sina Institute for Scientific and Industrial Research, Universiti Teknologi Malaysia, Johor, Malaysia; Institute For Artificial Intelligence and Big Data, Universiti Malaysia Kelantan, City Campus, Pengkalan Chepa, 16100 Kota Bharu, Kelantan, Malaysia
SITI ZAITON MOHD HASHIM Institute For Artificial Intelligence and Big Data, Universiti Malaysia Kelantan, City Campus, Pengkalan Chepa, Kota Bharu, Kelantan, Malaysia
Abstract
In essence, a biometric system comprises a pattern recognition system that obtains a person's biometric data from which a feature is set and then extracted. Upon setting the feature, it is compared to the template set stored in the database. Biometric identification systems need to not only have the capacity to distinguish between individuals but to also be capable of distinguishing individuals with nearly identical biometric signatures, such as identical twins. Multimodal biometric systems are therefore currently more popular because of their higher accuracy level in comparison to unimodal biometric systems in the context of identical twins. Comparatively, these systems require the extraction and selection of meaningful features. This paper introduces a new method for a multimodal biometric system using the Aspect United Moment Invariant for global feature extractions to detect identical twins. An experimental data set comprised of 1600 images from 100 pairs of identical twins collected from the Kurdistan region in Iraq is utilized.
Publication Details
Page(s) 2148-2157
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 98, Issue: 12, Year: 2020

Request the full text from PASTIC

Keywords
Identification, Multi-Biometric, Global Features, Identical Twin, Aspect United Moment Invariant (AUMI)
0

Citations

0

Downloads

25

Views