Histogram-based classifiers having variable bin sizes

Details Histogram-based classifiers having variable bin sizes Histogram-based classifiers having variable bin sizes

2007-07-13

2010-10-26

Holmes, Michael (Department: 2129)

Data processing: artificial intelligence

Neural network

Learning task

C706S059000

Reexamination Certificate

active

07822696

ABSTRACT:
A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive
egative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system. In additional embodiments, combination classifiers are trained using various combinations of weight trimming, bootstrapping, and a weak classifier termed a “fat stump” classifier.

REFERENCES:
patent: 5793888 (1998-08-01), Delanoy
patent: 6697504 (2004-02-01), Tsai
patent: 6757666 (2004-06-01), Thomas
patent: 6804391 (2004-10-01), Blake 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: 7139738 (2006-11-01), Philomin et al.
patent: 7164781 (2007-01-01), Kim et al.
patent: 7243063 (2007-07-01), Ramakrishnan et al.
patent: 7324671 (2008-01-01), Li et al.
patent: 7343028 (2008-03-01), Ioffe et al.
patent: 7508961 (2009-03-01), Chen et al.
patent: 7519200 (2009-04-01), Gokturk et al.
patent: 7526101 (2009-04-01), Avidan
patent: 7620818 (2009-11-01), Vetro et al.
patent: 7643659 (2010-01-01), Cao et al.
patent: 7657089 (2010-02-01), Li et al.
patent: 7668346 (2010-02-01), Xiao et al.
patent: 7693301 (2010-04-01), Li et al.
patent: 7707132 (2010-04-01), Xie et al.
patent: 2006/0126938 (2006-06-01), Lee et al.
patent: 2006/0248029 (2006-11-01), Liu et al.
patent: 2007/0011119 (2007-01-01), Thaler
patent: 2007/0019863 (2007-01-01), Ito
Response Binning: Improved Weak Classifiers for Boosting, Rasolzadeh, B.; Petersson, L.; Pettersson, N.; Intelligent Vehicles Symposium, 2006 IEEE Digital Object Identifier: 10.1109/IVS.2006.1689652 Publication Year: 2006 , pp. 344-349.
New Feature Vector for Image Retrieval: Sum of Value of Histogram Bins, Sai, N.S.T.; Patil, R.C.; Advances in Computing, Control, & Telecommunication Technologies, 2009. ACT '09. International Conference on Digital Object Identifier: 10.1109/ACT.2009.140 Publication Year: 2009 , pp. 550-554.
Dynamic three-bin real AdaBoost using biased classifiers: An application in face detection, Abiantun, R.; Savvides, M.; Biometrics: Theory, Applications, and Systems, 2009. BTAS '09. IEEE 3rd International Conference on Digital Object Identifier: 10.1109/BTAS.2009.5339038 Publication Year: 2009 , pp. 1-6.
Classification and Summarization of Pros and Cons for Customer Reviews, Hu, Xinghua; Wu, Bin; Web Intelligence and Intelligent Agent Technologies, 2009. WI-IAT '09. IEEE/WIC/ACM International Joint Conferences on vol. 3 Digital Object Identifier: 10.1109/WI-IAT.2009.234 Publication Year: 2009 , pp. 73-76.
Action Categorization in Soccer Videos Using String Kernels, Ballan, L.; Bertini, M.; Bimbo, A.D.; Serra, G.; Content-Based Multimedia Indexing, 2009. CBMI '09. Seventh International Workshop on Digital Object Identifier: 10.1109/CBMI.2009.10 Publication Year: 2009 , pp. 13-18.
Palmprint Identification using Boosting Local Binary Pattern, Xianji Wang; Haifeng Gong; Hao Zhang; Bin Li; Zhenquan Zhuang; Pattern Recognition, 2006. ICPR 2006. 18th International Conference on vol. 3 Digital Object Identifier: 10.1109/ICPR.2006.912 Publication Year: 2006 , pp. 503-506.
Bourdev, L., J. Brandt, Robust object detection via soft cascade, IEEE Comp. Society Conf. on Comp. Vision and Pattern Recognition, Jun. 20-25, 2005, pp. 236-243, vol. 2.
Brubaker, S. C., M. D. Mullin, and J. M. Rehg, Towards optimal training of cascaded detectors, Proc. of ECCV, 2006, pp. 325-337.
Friedman, J., T. Hastie, and R. Tibshirani, Additive logistic regression: A statistical view of boosting, Annals of Statistics, 2000, pp. 337-307, vol. 28.
Li, S. Z., L. Zhu, Z. Q. Zhang, A. Blake, H. J. Zhang, and H. Shum, Statistical learning of multi-view face detection, Proc. of the 7th European Conf. on Comp. Vision, 2002.
Luo, H., Optimization design of cascaded classifiers, IEEE Comp. Soc. Conf. on Comp. Vision and Pattern Recognition, CVPR'05, 2005, pp. 480-485, vol. 1.
Nowlan, S. and J. Platt, A convolutional neural network hand tracker, Advances in Neural Information Processing Systems 7, 1995, pp. 901-908, San Mateo, CA.
Rowley, H.A., S. Baluja and T. Kanade, Neural network-based face detection, IEEE Trans. on Pattern Analysis and Mach. Intelligence, Jan. 1998, pp. 23-28, vol. 20, No. 1.
Schapire, R. E., and Y. Singer, Improved boosting algorithms using confidence-rated predictions, Machine Learning, 1999, pp. 297-336, vol. 37.
{hacek over (S)}ochman, J., and J. Matas, Waldboost—Learning for time constrained sequential detection, Proc. of CVPR, 2005.
Sung, K., and T. Poggio, Example-based learning for view-based human face detection, IEEE Trans. on Pattern Analysis and Mach. Intelligence, Jan. 1998, pp. 39-51, vol. 20, No. 1.
Viola, P., and M. J. Jones, Rapid object detection using a boosted cascade of simple features, Proc. of IEEE Conf. on Comp. Vision and Pattern Recognition, 2001.
Viola, P., M. J. Jones, Robust real-time face detection, Int'l J. of Comp. Vision, May 2004, pp. 137-154, vol. 57, No. 2.
Viola, P., J. C. Platt, and C. Zhang, Multiple instance boosting for object detection, Proc. of NIPS, 2006, vol. 18.
Wu, B., H. Ai, C. Huang, and S. Lao, Fast rotation invariant multi-view face detection based on real adaboost, Proc. of IEEE Automatic Face and Gesture Recognition, 2004.
Wu, J., M. D. Mullin, J. M. Rehg, Linear Asymmetric Classifier for cascade detectors, Proceedings of the 22nd Int'l Conf. on Mach. Learning, 2005, vol. 119, pp. 988-995, Bonn, Germany.
Wu, J., J. M. Rehg, and M. D. Mullin, Learning a rare event detection cascade by direct feature selection, Advances in Neural Information Processing Systems, NIPS, 2003.
Xiao, R., L. Zhu, H.-J. Zhang, Boosting chain learning for object detection, 9th IEEE Int'l Conf. on Computer Vision, ICCV'03, 2003, vol. 1.
Wilbert L. Starks, U.S. Appl. No. 11/777,482, Office Action, Mar. 17, 2010.
Yan, R., and A. G. Hauptmann, Co-retrieval: A boosted reranking approach for video retrieval, IEEE Proceedings of Vision, Image and Signal Processing, Dec. 9, 2005, pp. 888-895, vol. 152, No. 6, IEEE Computer Society, Washington, DC, USA.
Kauchak, D., J. Smarr and C. Elkan, Sources of success for boosted wrapper induction, J. of Mach. Learning Research, May 2004, pp. 499-527, vol. 5, MIT Press.
Adrian L. Kennedy, U.S. Appl. No. 11/777,464, Office Action, Jun. 23, 2010.
Viola, P., and M. Jones, Fast and robust classification using asymmetric AdaBoost and a detector cascade, Advances in Neural Information Processing System, 2001, pp. 1311-1318, vol. 14, MIT Press.
Ji, C., and S. Ma, Combinations of weak classifiers, IEEE Transactions on Neural Networks, Jan. 1997, pp. 32-42, vol. 8, No. 1, IEEE Computer Society, Washington, DC, USA.
J. {hacek over (S)}chman and J. Matas, Inter-stage feature propagation in cascade building with AdaBoost, 17th Int'l Conf. on Pattern Recognition, Aug. 2004, pp. 236-239, vol. 1, IEEE Computer Society, Washington, DC, USA.
Lienhart, R., E. Kuranov and V. Pisarevsky, Empirical analysis of detection cascades of boosted classifiers for rapid object detection, DAGM 25th Pattern Recognition Symposium, Sep. 2003, pp. 297-304, Madgeburg, Germany.
Thompson, S., Pruning boosted classifiers with a real valued genetic algorithm, Knowledge-Based Systems, vol. 12, No. 5-6, Oct. 1999, pp. 277-284, Elsevier Science B.V.

Affiliated with

Also associated with

Rating

Histogram-based classifiers having variable bin sizes does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Histogram-based classifiers having variable bin sizes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Histogram-based classifiers having variable bin sizes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4241955