Hierarchical PSO-Adaboost Based Classifiers for Fast and Robust Face Detection
We propose a fast and robust hierarchical face detection system which finds and localizes face images with a cascade of classifiers. Three modules contribute to the efficiency of our detector. First, heterogeneous feature descriptors are exploited to enrich feature types and feature numbers for face representation. Second, a PSO-Adaboost algorithm is proposed to efficiently select discriminative features from a large pool of available features and reinforce them into the final ensemble classifier. Compared with the standard exhaustive Adaboost for feature selection, the new PSOAdaboost algorithm reduces the training time up to 20 times. Finally, a three-stage hierarchical classifier framework is developed for rapid background removal. In particular, candidate face regions are detected more quickly by using a large size window in the first stage. Nonlinear SVM classifiers are used instead of decision stump functions in the last stage to remove those remaining complex nonface patterns that can not be rejected in the previous two stages. Experimental results show our detector achieves superior performance on the CMU+MIT frontal face dataset.
[1] M. H. Yang, D. J. Kreigman, and N. Ahuja, "Detecting faces in images:
A survey," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.24, no.1, pp.34-58, Jan. 2002.
[2] P. Viola, and M. Jones, "Rapid object detection using a boosted cascade
of simple features," in Proc. of CVPR 2001, vol.1, 2001, pp.I-511- I-
518.
[3] P. Viola, and M. Jones, "Robust real-time face detection," International
Journal of Computer Vision, vol.57, no.2, pp.137-154, Jan. 2004.
[4] H. A. Rowley, S. Baluja, and T. Kanade, "Neural network based face
detection," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.20, no.1, pp.23-38, Jan. 1998.
[5] R. Féraud, O. Bernier, J. Viallet, and M. Collobert, "A fast and accurate
face detector based on neural networks," IEEE Trans. on Pattern
Analysis and Machine Intelligence, vol.23, no.1, pp.42-53, Jan. 2001.
[6] C. Garcia, and M. Delakis, "Convolutional face finder: A neural
architecture for fast and robust face detection," IEEE Trans. on Pattern
Analysis and Machine Intelligence, vol.26, no.11, pp.1408-1423, 2004.
[7] C. Huang, H. Z. Ai, B. Wu, and S. H. Lao, "Boosting nested cascade
detector for multi-view face detection," in Proc. of ICPR 2004, vol.2,
2004, pp.415-418.
[8] S. Z. Li, and Z. Zhang, "Floatboost learning and statistical face
detection," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.26, no.9, pp.1112-1123, Sep. 2004.
[9] S.Y.Yan, S.G.Shan, X.L.Chen, and W. Gao, "Locally Assembled Binary
(LAB) feature with feature-centric cascade for fast and accurate face
detection," in Proc.of CVPR 2008, 2008, pp.1-7.
[10] H. Schneiderman, "Feature-centric evaluation for efficient cascaded
object detection," in Proc. of CVPR 2004, vol.2, 2004, pp.29-36.
[11] M.T. Pham, and T.J. Cham, "Fast training and selection and Haar
features using statistics in boosting-based face detection," in Proc. of
ICCV 2007, 2007, pp.1-7.
[12] L.Zhang, R.Chu, S.Xiang, S.Liao, and S.Li, "Face detection based on
multi-block LBP representation," in Proc. of ICB 2007, 2007, pp.11-18.
[13] T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution gray scale
and rotation invariant texture analysis with local binary patterns," IEEE
Trans. on Pattern Analysis and Machine Intelligence, vol.24, no.7,
pp.971-987, July, 2002.
[14] H. Bay, A. Ess, T. Tuytelaars, and G. L. Van, "SURF: Speeded Up
Robust Features, " in Proc. of ECCV, Part(1), 2006, pp.404-417.
[15] H. Bay, A. Ess, T. Tuytelaars, and G. L. Van, "SURF: Speeded Up
Robust Features,"Computer Vision and Image Understanding, vol.110,
no.3, pp.346-359, June, 2008.
[16] Y. Freund, and R. E. Schapire, "Experiments with a new boosting
algorithm," in Proc. of ICML 1996, 1996, pp.148-156.
[17] J. Kennedy, and R.C.Eberhart, "Particle swarm optimization," in Proc.
of ICNN 1995, 1995, pp.1942-1948.
[1] M. H. Yang, D. J. Kreigman, and N. Ahuja, "Detecting faces in images:
A survey," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.24, no.1, pp.34-58, Jan. 2002.
[2] P. Viola, and M. Jones, "Rapid object detection using a boosted cascade
of simple features," in Proc. of CVPR 2001, vol.1, 2001, pp.I-511- I-
518.
[3] P. Viola, and M. Jones, "Robust real-time face detection," International
Journal of Computer Vision, vol.57, no.2, pp.137-154, Jan. 2004.
[4] H. A. Rowley, S. Baluja, and T. Kanade, "Neural network based face
detection," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.20, no.1, pp.23-38, Jan. 1998.
[5] R. Féraud, O. Bernier, J. Viallet, and M. Collobert, "A fast and accurate
face detector based on neural networks," IEEE Trans. on Pattern
Analysis and Machine Intelligence, vol.23, no.1, pp.42-53, Jan. 2001.
[6] C. Garcia, and M. Delakis, "Convolutional face finder: A neural
architecture for fast and robust face detection," IEEE Trans. on Pattern
Analysis and Machine Intelligence, vol.26, no.11, pp.1408-1423, 2004.
[7] C. Huang, H. Z. Ai, B. Wu, and S. H. Lao, "Boosting nested cascade
detector for multi-view face detection," in Proc. of ICPR 2004, vol.2,
2004, pp.415-418.
[8] S. Z. Li, and Z. Zhang, "Floatboost learning and statistical face
detection," IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol.26, no.9, pp.1112-1123, Sep. 2004.
[9] S.Y.Yan, S.G.Shan, X.L.Chen, and W. Gao, "Locally Assembled Binary
(LAB) feature with feature-centric cascade for fast and accurate face
detection," in Proc.of CVPR 2008, 2008, pp.1-7.
[10] H. Schneiderman, "Feature-centric evaluation for efficient cascaded
object detection," in Proc. of CVPR 2004, vol.2, 2004, pp.29-36.
[11] M.T. Pham, and T.J. Cham, "Fast training and selection and Haar
features using statistics in boosting-based face detection," in Proc. of
ICCV 2007, 2007, pp.1-7.
[12] L.Zhang, R.Chu, S.Xiang, S.Liao, and S.Li, "Face detection based on
multi-block LBP representation," in Proc. of ICB 2007, 2007, pp.11-18.
[13] T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution gray scale
and rotation invariant texture analysis with local binary patterns," IEEE
Trans. on Pattern Analysis and Machine Intelligence, vol.24, no.7,
pp.971-987, July, 2002.
[14] H. Bay, A. Ess, T. Tuytelaars, and G. L. Van, "SURF: Speeded Up
Robust Features, " in Proc. of ECCV, Part(1), 2006, pp.404-417.
[15] H. Bay, A. Ess, T. Tuytelaars, and G. L. Van, "SURF: Speeded Up
Robust Features,"Computer Vision and Image Understanding, vol.110,
no.3, pp.346-359, June, 2008.
[16] Y. Freund, and R. E. Schapire, "Experiments with a new boosting
algorithm," in Proc. of ICML 1996, 1996, pp.148-156.
[17] J. Kennedy, and R.C.Eberhart, "Particle swarm optimization," in Proc.
of ICNN 1995, 1995, pp.1942-1948.
@article{"International Journal of Information, Control and Computer Sciences:49247", author = "Hong Pan and Yaping Zhu and Liang Zheng Xia", title = "Hierarchical PSO-Adaboost Based Classifiers for Fast and Robust Face Detection", abstract = "We propose a fast and robust hierarchical face detection system which finds and localizes face images with a cascade of classifiers. Three modules contribute to the efficiency of our detector. First, heterogeneous feature descriptors are exploited to enrich feature types and feature numbers for face representation. Second, a PSO-Adaboost algorithm is proposed to efficiently select discriminative features from a large pool of available features and reinforce them into the final ensemble classifier. Compared with the standard exhaustive Adaboost for feature selection, the new PSOAdaboost algorithm reduces the training time up to 20 times. Finally, a three-stage hierarchical classifier framework is developed for rapid background removal. In particular, candidate face regions are detected more quickly by using a large size window in the first stage. Nonlinear SVM classifiers are used instead of decision stump functions in the last stage to remove those remaining complex nonface patterns that can not be rejected in the previous two stages. Experimental results show our detector achieves superior performance on the CMU+MIT frontal face dataset.
", keywords = "Adaboost, Face detection, Feature selection, PSO", volume = "5", number = "11", pages = "1160-6", }
