Integrating Faces and Soft-biometrics for Newborn Recognition

The problem of mixing, swapping and abduction is a very serious and challenging issue throughout the world. Traditional methods of biometric and non biometric techniques have their own limitations and fail to provide required level of security for newborn. A multimodal biometric system integrates information from multiple biometric sources to compensate for the limitations in performance of each individual biometric system. We propose an optimal framework for combining the matching scores from face and soft-biometrics to recognize newborn. The integration of face and soft-biometric traits results in an improvement of approximately . % over the face biometric system on a database of 210 newborn.