By Topic

An efficient multi-modal biometric person authentication system using Fuzzy Logic

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Vasuhi, S. ; Dept. of Electron. Eng., Anna Univ., Chennai, India ; Vaidehi, V. ; Babu, N.T.N. ; Treesa, T.M.

This paper proposes a system obtained through decision level fusion of two well known biometric sensors to identify a person namely, Fingerprint sensor and Voice sensor. More than one sensor is needed for critical or highly secured areas. This paper proposes a multiple sensor data fusion methodology using Fuzzy Logic (FL) approach. The finger prints recognition system uses orientation of the input image and cross correlation of the field orientation images. Orientation Field Methodology (OFM) has been used as a pre-processing module, and it converts the images into a field pattern based on the direction of ridges, loops and bifurcations in the image of finger print. The input image is then Cross Correlated (CC) with all the images in the cluster and the highest correlated image is taken as the output. As the proposed scheme uses Cross Correlation of Field Orientation (CCFO = OFM + CC) images for fingerprint identification, the result gives good recognition rate. Similarly, most voice recognition systems are speaker-dependent so, a speaker recognition system has been designed which involves feature extraction and classification systems. Mel-Frequency Cepstral Coefficient (MFCC) is the method used to extract the feature from the raw speech signal. The identity of the closest match found is treated as the corresponding identity for test speaker. The integrated system overcomes the drawbacks of each of the individual sensor. It is tested on MIT-AU database and the results are found to have better accuracy rates.

Published in:

Advanced Computing (ICoAC), 2010 Second International Conference on

Date of Conference:

14-16 Dec. 2010