Sequential Face and Voice Biometric System for Access Control into a Security Safe

The security safe is a place or building where classified document and precious items are kept. To prevent unauthorised persons from gaining access to this safe a lot of technologies had been used. But frequent reports of an unauthorised person gaining access into security safes with the aim of removing document and items from the safes are pointers to the fact that there is still that security gap in the recent technologies used as access control for the security safe. This work is a Sequential Multimodal Biometric System based on deep learning technique that used a pre - trained Alexnet convolutional neural network CNN. The developed system was trained on both face images and voice signals of 50 candidates. The face biometrics of those candidates was first captured by a camera while the user?s speech data were also captured by a microphone unit. The captured data were registered and stored in two different databases. The pre-trained deep - learning model CNN was trained in a MATLAB 2020 platform with face and voice data in the database for feature Extraction and recognition. The safe was accessed in a sequential order by the combination of face and voice pattern recognition. A failure - rate of 0.02%. was obtained to give access to authorised users while declining unauthorised person access to the security safe.