Paper Title
Person Authentication Using Face And Voice Modalities
Abstract
the paper deals with face recognition and speaker recognition algorithms and their application for enhanced
multimodal biometrics authentication approach to achieve better performance. Biometric technologies refer to identifying
individuals based on their distinguishing biological or behavioral traits such as face, speech, fingerprints, retina, iris, etc. The
convenience of biometric security systems and their acceptable authentication performance have led to the integration of
biometric systems into desktops, laptops, PDAs and mobilephones. A multimodal personal authentication approach that
combines information obtained from face and voice modalities is presented in this paper. In this work, a computationally
efficient Principal Component Analysis using Eigen faces algorithm is used for face recognition and in voice authentication,
pitch frequency and the Mel frequency cepstral coefficients (MFCC) are employed as voice features, and the K-means
clustering algorithm is applied to represent the voice signal. The performance of the algorithms is evaluated through
computer simulations and is found to be quite effective.