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

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.