A soft computing approach for feature selection and recognition in multi modal biometrics

Abstract

newlineBiometric systems identify a person through physical traits or verify his her identity through automatic processes. In these systems the biometric characteristics such as fingerprints, palmprint iris or speech can be recorded and are compared with the samples for the identification or verification Systems which use biometric measures are more secure because newlineit does not recognize a person by the things carried such as smart cards which newlineare used in the conventional authorization systems The advantages of the newlinebiometric identifiers are they cannot be mislaid forgotten guessed or easily newlinecopied For successful biometric systems implementation it has to address newlineissues like efficiency accuracy applicability robustness and universality newlineSingle modality based recognition verifications are not robust while newlinecombining information from different biometric modalities ensures better newlineperformance Multimodal biometric systems use multiple biometrics and newlineintegrate information for identification It compensates unimodal biometric newlinesystems limitations This study considers multimodal biometrics based on newlinefingerprint and finger veins Recognition based on the multiple biometrics is an emerging trend in newlineall the fields The strong reason for combining different modalities in the newlineidentification is to enhance the recognition rate This can be achieved when newlinedifferent statistically independent biometric features are combined or fused newlineMultimodal systems reduce failure to enroll and resist spoofing as multiple newlinebiometric sources cannot be spoofed simultaneously Multimodal systems newlinesearch large databases quickly through a less accurate modality to narrow down newlinedatabase options before applying complex and accurate modality on remaining newlinedata for final identification newline