Title :
Blind face indexing in video
Author_Institution :
Fac. of Electr. Eng. & Commun., Brno Univ. of Technol., Brno, Czech Republic
Abstract :
This paper deals with the proposal of blind face indexing system for real videos with no prior knowledge. The system consists of face and facial features detection and tracking stage and face clustering stage. Viola-Jones object detector for face detection, pictorial structures for facial feature detection and Lucas-Kanade optical flow for facial feature tracking are used. Average face models based on popular SIFT features are applied for face clustering. The system operates well on discussion talks or records of videoconferences.
Keywords :
image segmentation; indexing; object detection; pattern clustering; tracking; video signal processing; Lucas-Kanade optical flow; SIFT features; Viola-Jones object detector; average face model; blind face indexing system; face clustering stage; face features detection; facial feature tracking; facial features detection; pictorial structures; videoconference; Face; Face recognition; Facial features; Feature extraction; Indexing; Lighting; Clustering; SIFT keypoints and descriptors; face detection; facial feature;
Conference_Titel :
Telecommunications and Signal Processing (TSP), 2011 34th International Conference on
Conference_Location :
Budapest
Print_ISBN :
978-1-4577-1410-8
DOI :
10.1109/TSP.2011.6043664
