Multi-Biometric Person Authentication System Using Speech, Signature And Handwriting Features

-------------------------------------------------------------ABSTRACT-------------------------------------------------------Biometric Technologies are automated methods for verifying or recognizing the identity of a living person based on physiological or behavioral characteristics. Multimodal Biometric Systems are those which utilize more than one physiological or behavioral characteristic for enrollment, verification or identification. Speaker Recognition is the task of recognizing the speakers using their speech signal. Mel Frequency Cepstral Coefficients (MFCCs) of speaker is determined by extracting and analyzing speaker – specific features from the speech signal. Signature Recognition is the task of recognizing signatories by using their signatures. Features like Horizontal Projection Profile (HPP), Vertical Projection Profile (VPP) and Discrete Cosine Transform (DCT) are determined. Handwriting biometric feature can also be used for person authentication, since handwriting has been trained during initial days of learning of language; it is possible to find more regular and reliable results using this feature. In this project, we develop a Multimodal Biometric System using speech, signature and handwriting features, with the objective of improving performance and robustness. For identification and verification, we use MATLAB 7.14 to determine MFCC, HPP, VPP, DCT coefficients. KeywordsBiometrics; Speaker recognition; Signature recognition; Handwriting recognition; Multimodal system. --------------------------------------------------------------------------------------------------------------------------------------Date of Submission: 06 June 2014 Date of Publication: 20 June 2014 ---------------------------------------------------------------------------------------------------------------------------------------