Biometric authentication using facial recognition

Biometric authentication has been gaining popularity for providing privacy and security in many applications including secure access control, surveillance systems, user identification and many more. This research proposes a robust scheme for biometric authentication by analyzing and interpreting facial image using a neural network. Human face has become as the key attribute for biometric authentication over the recent years due to its uniqueness and robustness. Our system focuses on efficient detection and recognition of user’s face for precise authentication. The facial features of a user are compared with a face database in order to perform matching for authentication and authorization. The proposed system estimates the face by analyzing skin color components in the facial image. The facial edge features are then extracted from the detected face skeleton. A neural network is employed and trained with the extracted edge features to recognize the user face by comparing with the facial database. Once the user is identified, authentication is granted. Experimental evaluation demonstrates that our proposed system provides better performance meeting accuracy requirements and less computation time.