000082981 001__ 82981
000082981 005__ 20190316233705.0
000082981 037__ $$aREP_WORK
000082981 245__ $$aReal-Time Face Detection Using Boosting Learning in Hierarchical Feature Spaces
000082981 269__ $$a2003
000082981 260__ $$aMartigny, Switzerland$$bIDIAP$$c2003
000082981 336__ $$aReports
000082981 500__ $$aPublished in ``the International Conference on Pattern Recognition (ICPR)'', August, 2003
000082981 520__ $$aBoosting-based methods have recently led to the state-of-the-art face detection systems. In these systems, weak classifiers to be boosted are based on simple, local, Haar-like features. However, it can be empirically observed that in later stages of the boosting process, the non-face examples collected by bootstrapping become very similar to the face examples, and the classification error of Haar-like feature-based weak classifiers is thus very close to 50\%. As a result, the performance of a face detector cannot be further improved. This paper proposed a solution to this problem, introducing a face detection method based on boosting in hierarchical feature spaces (both local and global). We argue that global features, like those derived from Principal Component Analysis, can be advantageously used in the later stages of boosting, when local features do not provide any further benefit, without affecting computational complexity. We show, based on statistics of face and non-face examples, that weak classifiers learned in hierarchical feature spaces are better boosted. Our methodology leads to a face detection system that achieves higher performance than the current state-of-the-art system, at a comparable speed.
000082981 6531_ $$avision
000082981 6531_ $$azhang
000082981 700__ $$aZhang, Dong
000082981 700__ $$aLi, S. Z.
000082981 700__ $$0241066$$aGatica-Perez, Daniel$$g171600
000082981 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2003/rr-03-70.pdf$$zURL
000082981 8564_ $$s262212$$uhttps://infoscience.epfl.ch/record/82981/files/rr-03-70.pdf$$zn/a
000082981 909C0 $$0252189$$pLIDIAP$$xU10381
000082981 909CO $$ooai:infoscience.tind.io:82981$$pSTI$$preport$$qGLOBAL_SET
000082981 937__ $$aEPFL-REPORT-82981
000082981 970__ $$azhang-rr-03-70/LIDIAP
000082981 973__ $$aEPFL$$sPUBLISHED
000082981 980__ $$aREPORT