2층 구조를 이용한 실시간 얼굴추적

This paper is presented 2-layer algorithm for tracking human faces in real time. The framework provides the structure which offers a means for automatic tracking initialization and reinitialization when environmental conditions momentarily deteriorate and cause the system to lose track of its target. When upper layer fails to track its object, lower layer helps it for tracking one continuously. In other words, lower layer allows the system to return approximate information on feature location or configuration.