Fast Transformation-Invariant Component Analysis
International Journal of Computer Vision
A novel face detection method based on contourlet features
ICIC'09 Proceedings of the 5th international conference on Emerging intelligent computing technology and applications
On asymmetric classifier training for detector cascades
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II
An effective news anchorperson shot detection method based on adaptive audio/visual model generation
CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval
Face detection method based on kernel independent component analysis and boosting chain algorithm
ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
| Hi-index | 0.00 |
In this paper, we present a system which learns to detectmulti-view faces.The system uses a coarse-to-fine, simple-to-complex architecture called detector-pyramid.A new boosting algorithm, called FloatBoost, is proposed to construct a strong face-nonface classifier from weak classifiersfor the component detectors in the pyramid.FloatBoost incorporates the idea of Floating Search [22 ] into AdaBoost[9,26 ], and yields similar or higher classification accuracythan AdaBoost with a smaller number of weak classifiers.This work leads to the first real-time multi-view face detection system in the world.It runs at 200 ms per image of size320x240 pixels on a Pentium-III CPU of 700 MHz.Alivedemo will be shown at the conference.