A detector is built in order to recognize faces. To train the detector, a set of face and non-face training images are used. For example:
The face training set consisted of 4916 hand labeled faces scaled and aligned to a base resolution of 24 by 24 pixels. The non-face subwindows used to train the detector come from 9544 images which were manually inspected and found to not contain any faces [1].
So this detector is designed to only detect faces. But you can train the detector to detect eyes, mouth,....
[1] Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on (Vol. 1, pp. I-511). IEEE.
Asked: 2013-07-01 23:18:44 -0600
Seen: 132 times
Last updated: Jul 02 '13
please clarify, if you're talking about detection ( are there faces, where, and how many ) or recognition ( who is it )
a cascade based detection will return several faces, while the recognition will return the closest match from the training set.
Hardik, haar-like features are commonly used for face (or object) detection, but they can be used for face (object) recognition also. Check this paper: (The proposed system in this paper introduces the novel idea of using Haar-like features, which have commonly been used for object detection, along with a probabilistic classifier for face recognition.)
Nasrollahi, K., & Moeslund, T. B. HAAR-LIKE FEATURES FOR ROBUST REAL-TIME FACE RECOGNITION.
So, face detection and recognition are two different things
albertofernandez, did you find a free version of above paper ?
http://vbn.aau.dk/files/77951262/icip_2013.pdf
thanks a ton ;)