Face Detection using AdaBoost
2009
In this paper, a fast and efficient face detection method is presented which relies on the AdaBoost algorithm and the features of Haar. Using rectangle features to calculate each value with non-face image's characteristic value at the same position of the rectangle feature. Through boosting algorithm to train a classifier that make up of several rectangle features which could separate face and non-face images exactly. The simple classifiers contains simple rectangle features which are reminiscent of Haar basis. Their simplicity and a new image representation called Integral Image allow a very quick computing of these Haar-like features. AdaBoost train need very long time, using hardware (VHDL) to solve the problem.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI