Cyber Security Biometric Solution Using Automatic Matching and Deep Learning

Biometrics is an alternative solution to the old means of identity verification, such as access cards. However, monomodal biometric systems suffer from multiple limitations, noise introduced by sensor and non-universality. Multi-biometrics allows us overcome these problems thus obtain better performance. Multimodal biometrics, using deep learning, has recently gained interest over single modalities. In this work, we propose a learning model for persons identification/verification Face Iris traits. The features iris face are extracted utilizing DenseNet121 FaceNet models, merged feature-level fusion scheme. We also proposed new automatic matching technique verify person’s identity. results presented in paper show approaches recognition, especially when models pre-trained. highlighted DenseNet121-FaceNet method compared standard threshold selection according Equal Error Rate point.