Human detection and localization in secure access control by analysing facial features

Accurate detection and position estimation of human objects is essential in many security applications including door access control, surveillance monitoring, intrusion detection, alarm monitoring and so on. This paper proposes an efficient approach for human detection and localization in secure access control by analysing facial features. The proposed technique captures the video scenes using a stereo camera pair: left and right camera. The system first tracks the human by detecting the face area from the video scenes using a robust fuzzy face tracking algorithm. A neural network is used to match the correspondence points between the left and right face sequences. The depth information is extracted from the matching result that localizes the human position. The position of the human can be used to estimate the intention of the human towards accessing the entrance. Experimental evaluation on real data sets demonstrates the robustness and efficiency of our proposed approach.