Image analysis – Applications – Personnel identification
Reexamination Certificate
2007-06-07
2010-11-30
Perungavoor, Sath V (Department: 2624)
Image analysis
Applications
Personnel identification
C382S224000
Reexamination Certificate
active
07844085
ABSTRACT:
Systems and methods for training an AdaBoost based classifier for detecting symmetric objects, such as human faces, in a digital image. In one example embodiment, such a method includes first selecting a sub-window of a digital image. Next, the AdaBoost based classifier extracts multiple sets of two symmetric scalar features from the sub-window, one being in the right half side and one being in the left half side of the sub-window. Then, the AdaBoost based classifier minimizes the joint error of the two symmetric features for each set of two symmetric scalar features. Next, the AdaBoost based classifier selects one of the features from the set of two symmetric scalar features for each set of two symmetric scalar features. Finally, the AdaBoost based classifier linearly combines multiple weak classifiers, each of which corresponds to one of the selected features, into a stronger classifier.
REFERENCES:
patent: 5163094 (1992-11-01), Prokoski et al.
patent: 5574573 (1996-11-01), Ray et al.
patent: 5629752 (1997-05-01), Kinjo
patent: 5680481 (1997-10-01), Prasad et al.
patent: 5715325 (1998-02-01), Bang et al.
patent: 5850470 (1998-12-01), Kung et al.
patent: 5892837 (1999-04-01), Luo et al.
patent: 6463163 (2002-10-01), Kresch
patent: 6633655 (2003-10-01), Hong et al.
patent: 7024033 (2006-04-01), Li et al.
patent: 7050607 (2006-05-01), Li et al.
patent: 7099510 (2006-08-01), Jones et al.
patent: 7194114 (2007-03-01), Schneiderman
patent: 7379568 (2008-05-01), Movellan et al.
patent: 7471812 (2008-12-01), Cho et al.
patent: 7505621 (2009-03-01), Agrawal et al.
patent: 7508961 (2009-03-01), Chen et al.
patent: 7519200 (2009-04-01), Gokturk et al.
patent: 7587069 (2009-09-01), Movellan et al.
patent: 7643659 (2010-01-01), Cao et al.
patent: 7680330 (2010-03-01), Leung
patent: 7773781 (2010-08-01), Kim
patent: 7783086 (2010-08-01), Sabe et al.
patent: 7792335 (2010-09-01), Steinberg et al.
patent: 2005/0102246 (2005-05-01), Movellan et al.
patent: 2005/0213810 (2005-09-01), Sabe et al.
patent: 2005/0220336 (2005-10-01), Sabe et al.
patent: 2006/0050933 (2006-03-01), Adam et al.
patent: 2006/0104517 (2006-05-01), Ko et al.
patent: 2008/0008362 (2008-01-01), Hu
patent: 2008/0304714 (2008-12-01), Lu et al.
Liu, T., Zheng, N., Zhao, L., Cheng, H., “Learning based symmetric features selection for vehicle detection”, Intelligent Vehicles Symposium, 2005. Proceedings. IEEE, pp. 124-129, ISBN: 0-7803-8961-1.
Viola, P., Jones, M.J., “Robust Real-Time Face Detection”, International Journal of Computer Vision 57(2), pp. 137-154, 2004.
Lu Juwei
Zhou Hui
Perungavoor Sath V
Seiko Epson Corporation
Watson Mark P.
LandOfFree
Pairwise feature learning with boosting for use in face... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pairwise feature learning with boosting for use in face..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pairwise feature learning with boosting for use in face... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4252350