Bimodal Biometric Person Authentication System Using Speech and Signature Features

International Journal of Biometric and Bioinformatics 01/2010;
Source: DOAJ

ABSTRACT Biometrics offers greater security and convenience than traditional methods of person authentication. Multi biometrics has recently emerged as a means of more robust and efficient person authentication scheme. Exploiting information from multiple biometric features improves the performance and also robustness of person authentication. The objective of this paper is to develop a robust bimodal biometric person authentication system using speech and signature biometric features. Speaker based unimodal system is developed by extracting Mel Frequency Cepstral Coefficients (MFCC) and Wavelet Octave Coefficients of Residues (WOCOR) as feature vectors. The MFCCs and WOCORs from the training data are modeled using Vector Quantization (VQ) and Gaussian Mixture Modeling (GMM) techniques. Signature based unimodal system is developed by using Vertical Projection Profile (VPP), Horizontal Projection Profile (HPP) and Discrete Cosine Transform (DCT) as features. A bimodal biometric person authentication system is then built using these two unimodal systems. Experimental results show that the bimodal person authentication system provides higher performance compared with the unimodal systems. The bimodal system is finally evaluated for its robustness using the noisy data and also data collected from the real environments. The robustness of the bimodal system is more compared to the unimodal person authentication systems.

1 Follower
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we use Genetic and Evolutionary Computation (GEC) to optimize the weights assigned to the biometric modalities of a multi-biometric system for score-level fusion. Our results show that GEC-based multi-biometric fusion provides a significant improvement in the recognition accuracy over evenly fused biometric modalities, increasing the accuracy from 90.77% to 95.24%.
    Evolutionary Computation (CEC), 2011 IEEE Congress on; 07/2011
  • Source
    • "However, when these systems are applied to real-world applications, their performance can be affected by numerous factors such as noisy sensor data due to dust or lighting conditions and spoofing. Multibiometric systems that fuse multiple biometric modalities have been shown to be more robust, able to counter many of the aforementioned limitations, and are also capable of achieving higher recognition accuracies (Jain, Nandakumar, Ross 2005; Ross 2007; Eshwarappa and Latte 2010). "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we investigate the use of a hybrid genetic feature weighting and selection (GEFeWS) algorithm for multi-biometric recognition. Our results show that GEFeWS is able to achieve higher recognition accuracies than using genetic-based feature selection (GEFeS) alone, while using significantly fewer features to achieve approximately the same accuracies as using genetic-based feature weighting (GEFeW).
    Proceedings of The 22nd Midwest Artificial Intelligence and Cognitive Science Conference 2011, Cincinnati, Ohio, USA, April 16-17, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: This research examines whether the integration of facial and fingerprint biometrics can improve the performance in financial infrastructure security such as ATM protection. Fingerprint biometrics consider distorted and misaligned fingerprints caused by environmental noise such as oil, wrinkles, dry skin, dirt and displacement of the query fingerprint with the database fingerprint template during matching. The noisy, distorted and/or misaligned fingerprint produced as a 2-D on x-y image, is enhanced and optimized using a new hybrid Modified Gabor Filter-Hierarchal Structure Check (MGF-HSC) system model based on an MGF integrated with an HSC. However, in order to improve the accuracy of financial infrastructure, face biometrics are introduced using a fast principal component analysis algorithm, in which different face conditions such as lighting, blurriness, pose, head orientation and other conditions are addressed. The MGF-HSC approach minimizes false fingerprint matching and the dominant effect of distortion and misalignment of fingerprints to an acceptable level. The proposed bimodal biometrics increase the accuracy of the False Rejection Rate (FRR) to 98% when the False Acceptance Rate (FAR) is 0.1% in an experiment conducted with 1000 test cases. This result shows that facial biometrics can be used to support fingerprint biometrics for improving financial security based on with significant improvement in both FRR and FAR.
    2013 Information Security for South Africa; 08/2013
Show more


Available from