Identity verification using audio-visual features

A simple straightforward strategy to build a security system using audio-visual clues is proposed. A series of face and audio-visual verification is used to construct the system. The practical considerations that lead to specific data representation methods, design procedure, decision making criteria and subjective performance evaluation criteria involved in the research is illustrated. An account of the reasons behind choosing the used features and neural network architectures is included. Preliminary results of testing some of the nodes of the system on their members as well as intruders are shown.