A Novel Approach Towards Biometric Recognition System Using Voice and Signature

Abstract

Recently, recognition systems have gained importance due to their vital role in security by identifying users while interacting with electronic devices to ensure reliability. The typical authentication systems based on PINs or passwords have revealed various issues of deceitful access. On the contrary, Biometrics can establish an apparent discrepancy between a genuine individual and a fraudulent imitator. Biometrics may be categorized as a Single Model or Multimodal System. Systems of Multimodal bio-metrics are used in Physical Access, Civil ID, Criminal ID, Network/PC Access, Kiosk/ATM, Retail/POS, Surveillance, e-commerce, and telephony. This paper proposes a novel and robust recognition system that uses voice and signatures as inputs to recognize the users. The proposed method uses (Mel Frequency Cepstral Coefficients) MFCC and (Vector Quantization) VQ as characteristic vectors to perform voice analysis, and Vertical Projection Profile (VPP), Horizontal Projection Profile (HPP), and Discrete Cosine Transform (DCT) features to design an offline signature identification system. In the design, a similarity score is obtained. False acceptance and rejection probabilities are measured based on the highest score for each uni-model system. Finally, both methods are merged to get an equal error rate, which is used to evaluate the effectiveness of the proposed approach. The results indicate that when compared with unimodal biometric systems, the proposed multi-model biometric system produces less EER, making the system more robust and reliable.