Automatic detection and tracking of multiple individuals using multiple cues

PURPOSE: A method for automatic detection and tracking of multiple individuals using multiple cues is provided to detect multiple individuals accurately by tracking the face automatically. CONSTITUTION: A method for automatic detection and tracking of multiple individuals includes receiving of a frame of video and audio contents(202) and identifying a candidate area for a new face region in the frame(206). Whether the face of an individual is in the candidate area or not, is verified by using one or a plurality of hierarchical verification levels. When the face of the individual is in the candidate zone on one or a plurality of hierarchical verification levels, the face is displayed to be included in the candidate zone. Each face verified from frame to frame in the video contents is tracked by using multiple audio cues and/or video cues.