Fusion Method with Mean-discrete Algorithm in Feature level for Identical twins Identification

Abstract

The study on twins is an important form of study in the forensic and biometrics field as twins share similar genetic traits. A biometric is one of the common types of pattern recognition which acquires biometric data from a person. From these data, a feature is established and extracted where these features can be used to identify individual. Exiting works in biometric identification concentrate on unimodal biometric identification. The high similarity in a pair of twin’s biometric may lead to miss performance. Hence, due to their great accurateness, multimodal biometric systems have become more favored than unimodal biometric systems in identical twins identification. However, these systems are highly complex. We proposed Mean-Discrete feature based fusion algorithm for Kurdish handwriting and fingerprint for identical twins detection. Its viability and advantage over the unimodal biometric systems are highlighted. This paper employed 800 images from 50 pairs of identical twins from Kurdistan Region to carry out the experiment.