Acceleration Technique for Boosting Classification and its Application to Face Detection

Masanori Kawakita, Ryota Izumi, Jun'ichi Takeuchi, Yi Hu, Tetsuya Takamori, Hirokazu Kameyama
Proceedings of the Asian Conference on Machine Learning, PMLR 20:335-349, 2011.

Abstract

We propose an acceleration technique for boosting classification without any loss of classification accuracy and apply it to a face detection task. In classification task, much effort has been spent on improving the classification accuracy and the computational cost of training. In addition to them, the computational cost of classification itself can be critical in several applications including face detection. In face detection, a celebrating work by Viola and Jones (2001) developed a significantly fast face detector achieving a competitive accuracy with all preceding face detectors. In their algorithm, the cascade structure of boosting classifier plays an important role. In this paper, we propose an acceleration technique for boosting classifier. The key idea of our proposal is the fact that one can determine the sign of discriminant function before all weak learners are evaluated in general. An advantage is that our algorithm has no loss in classification accuracy. Another advantage is that our proposal is a unsupervised learning so that it can treat a covariate shift situation. We also apply our proposal to each cascaded boosting classifier in Viola and Jones type face detector. As a result, our proposal succeeds in reducing the classification cost by 20%.

Cite this Paper

BibTeX
@InProceedings{pmlr-v20-kawakita11, title = {Acceleration Technique for Boosting Classification and its Application to Face Detection}, author = {Kawakita, Masanori and Izumi, Ryota and Takeuchi, Jun'ichi and Hu, Yi and Takamori, Tetsuya and Kameyama, Hirokazu}, booktitle = {Proceedings of the Asian Conference on Machine Learning}, pages = {335--349}, year = {2011}, editor = {Hsu, Chun-Nan and Lee, Wee Sun}, volume = {20}, series = {Proceedings of Machine Learning Research}, address = {South Garden Hotels and Resorts, Taoyuan, Taiwain}, month = {14--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v20/kawakita11/kawakita11.pdf}, url = {https://proceedings.mlr.press/v20/kawakita11.html}, abstract = {We propose an acceleration technique for boosting classification without any loss of classification accuracy and apply it to a face detection task. In classification task, much effort has been spent on improving the classification accuracy and the computational cost of training. In addition to them, the computational cost of classification itself can be critical in several applications including face detection. In face detection, a celebrating work by Viola and Jones (2001) developed a significantly fast face detector achieving a competitive accuracy with all preceding face detectors. In their algorithm, the cascade structure of boosting classifier plays an important role. In this paper, we propose an acceleration technique for boosting classifier. The key idea of our proposal is the fact that one can determine the sign of discriminant function before all weak learners are evaluated in general. An advantage is that our algorithm has no loss in classification accuracy. Another advantage is that our proposal is a unsupervised learning so that it can treat a covariate shift situation. We also apply our proposal to each cascaded boosting classifier in Viola and Jones type face detector. As a result, our proposal succeeds in reducing the classification cost by 20%.} }
Endnote
%0 Conference Paper %T Acceleration Technique for Boosting Classification and its Application to Face Detection %A Masanori Kawakita %A Ryota Izumi %A Jun'ichi Takeuchi %A Yi Hu %A Tetsuya Takamori %A Hirokazu Kameyama %B Proceedings of the Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2011 %E Chun-Nan Hsu %E Wee Sun Lee %F pmlr-v20-kawakita11 %I PMLR %P 335--349 %U https://proceedings.mlr.press/v20/kawakita11.html %V 20 %X We propose an acceleration technique for boosting classification without any loss of classification accuracy and apply it to a face detection task. In classification task, much effort has been spent on improving the classification accuracy and the computational cost of training. In addition to them, the computational cost of classification itself can be critical in several applications including face detection. In face detection, a celebrating work by Viola and Jones (2001) developed a significantly fast face detector achieving a competitive accuracy with all preceding face detectors. In their algorithm, the cascade structure of boosting classifier plays an important role. In this paper, we propose an acceleration technique for boosting classifier. The key idea of our proposal is the fact that one can determine the sign of discriminant function before all weak learners are evaluated in general. An advantage is that our algorithm has no loss in classification accuracy. Another advantage is that our proposal is a unsupervised learning so that it can treat a covariate shift situation. We also apply our proposal to each cascaded boosting classifier in Viola and Jones type face detector. As a result, our proposal succeeds in reducing the classification cost by 20%.
RIS
TY - CPAPER TI - Acceleration Technique for Boosting Classification and its Application to Face Detection AU - Masanori Kawakita AU - Ryota Izumi AU - Jun'ichi Takeuchi AU - Yi Hu AU - Tetsuya Takamori AU - Hirokazu Kameyama BT - Proceedings of the Asian Conference on Machine Learning DA - 2011/11/17 ED - Chun-Nan Hsu ED - Wee Sun Lee ID - pmlr-v20-kawakita11 PB - PMLR DP - Proceedings of Machine Learning Research VL - 20 SP - 335 EP - 349 L1 - http://proceedings.mlr.press/v20/kawakita11/kawakita11.pdf UR - https://proceedings.mlr.press/v20/kawakita11.html AB - We propose an acceleration technique for boosting classification without any loss of classification accuracy and apply it to a face detection task. In classification task, much effort has been spent on improving the classification accuracy and the computational cost of training. In addition to them, the computational cost of classification itself can be critical in several applications including face detection. In face detection, a celebrating work by Viola and Jones (2001) developed a significantly fast face detector achieving a competitive accuracy with all preceding face detectors. In their algorithm, the cascade structure of boosting classifier plays an important role. In this paper, we propose an acceleration technique for boosting classifier. The key idea of our proposal is the fact that one can determine the sign of discriminant function before all weak learners are evaluated in general. An advantage is that our algorithm has no loss in classification accuracy. Another advantage is that our proposal is a unsupervised learning so that it can treat a covariate shift situation. We also apply our proposal to each cascaded boosting classifier in Viola and Jones type face detector. As a result, our proposal succeeds in reducing the classification cost by 20%. ER -
APA
Kawakita, M., Izumi, R., Takeuchi, J., Hu, Y., Takamori, T. & Kameyama, H.. (2011). Acceleration Technique for Boosting Classification and its Application to Face Detection. Proceedings of the Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 20:335-349 Available from https://proceedings.mlr.press/v20/kawakita11.html.

Related Material