Region pair grey difference classifier for face detection

Abstract

A new kind of region pair grey difference classifier was proposed. The regions in pairs associated to form a feature were not necessarily directly-connected, but were selected dedicatedly to the grey transition between regions coinciding with the face pattern structure. Fifteen brighter and darker region pairs were chosen to form the region pair grey difference features with high discriminant capabilities. Instead of using both false acceptance rate and false rejection rate, the mutual information was used as a unified metric for evaluating the classifying performance. The parameters of specified positions, areas and grey difference bias for each single region pair feature were selected by an optimization processing aiming at maximizing the mutual information between the region pair feature and classifying distribution, respectively. An additional region-based feature depicting the correlation between global region grey intensity patterns was also proposed. Compared with the result of Viola-like approach using over 2 000 features, the proposed approach can achieve similar error rates with only 16 features and 1/6 implementation time on controlled illumination images.

Keywords

face detection / region pair grey feature / region grey pattern correlation / machine learning

References

[1] Yang G., Huang T. S. Human face detection in complex background[J]. Pattern Recognition, 1994, 27(1): 53-63.

[2] Sirohey S. A. Human Face Segmentation and Identification[D]. 1993, Maryland: Computer Version Laboratory Center for Automation Research, University of Maryland.

[3] Yow K. C., Cipolla R. Feature-based human face detection[J]. Image and Vision Computing, 1997, 15(9): 713-735.

[4] Sumi Y, Ohta Y. Detection of face orientation and facial components using distributed appearance modeling [C]. In: Proc Int Workshop on Automatic Face and Gesture Recognition. Zurich, 1995. 254–259.

[5] Papageorgiou C, Oren M, Poggio T. A general framework for object detection[C]. In: International Conference on Computer Vision. India, 1998. 555–562.

[6] Rowley H., Baluja S., Kanade T. Neural network-based face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 23-38.

[7] Sung K., Poggio T. Example-based learning for view-based human face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-51.

[8] Yang M. H., David K., Narendra A. Detecting faces in images: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(1): 34-58.

[9] Yang M. H. Recent Advances in Face Detection[M]. 2004, United Kingdom: Tutorial Cambridge.

[10] Paul V., Michael Jones. Rapid object detection using a boosted cascade of simple features[J]. IEEE Computer Vision and Pattern Recognition CVPR, 2001, 1 511-518.

[11] Paul V., Michael Jones. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2): 137-154.

[12] Li Stan Z., Zhang Zhengqiu. Floatboost learning and statistical face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1112-1123.

[13] Ou Z., Tang X., Su Tieming. Cascade adaboost classifiers with stage optimization for face detection[J]. Lecture Notes in Computer Science, 2006, 3832 121-128.

[14] Le D.-D., Satoh Shin’ichi. A multi-stage approach to fast face detection[J]. IEICE Transactions on Information and Systems, 2006, 89(7): 2275-2285.

[15] Charles Brubacker S., Wu J., Sun J., et al. On the design of cascade of boosted ensembles for face detection[J]. International Journal of Computer Vision, 2008, 77(1–3): 65-86.

[16] CAS-PEAL Face Database[EB/OL]. http://www.jdl.ac.cn/peal/index.Html, 2009-03-20.

[17] Gao W, Cao B, Shan S. The CAS-PEAL Large-Scale Chinese Face Database and Evaluation Protocols[EB/OL]. http://www.jdl.ac.cn/tr/JDL-TR-04-FR-001.pdf, 2009-03-20.

[18] BioID Face Database[EB/OL]. http://www.bioid.com/downloads/facedb/, 2009-03-20.

[19] MIT-CBCL Face Database[EB/OL]. http://www.ai.mit.edu/projects/cbcl, 2009-03-20.

[20] FRGC Face Database[EB/OL]. http://face.nist.gov/frgc/, 2009-03-20.

[21] OpenCV[EB/OL]. http://sourceforge.net/projects/opencvlibrary, 2008-10-24.