Object detection and recognition with bayesian boosting

Details Object detection and recognition with bayesian boosting Object detection and recognition with bayesian boosting

2011-05-24

2011-05-24

Fernandez Rivas, Omar F (Department: 2129)

Data processing: artificial intelligence

Neural network

Learning task

C706S045000, C706S046000, C706S047000, C706S048000, C706S062000, C382S155000, C382S156000, C382S157000, C382S158000, C382S159000, C382S160000, C382S168000, C382S169000, C382S170000, C382S181000

Reexamination Certificate

active

07949621

ABSTRACT:
An efficient, effective and at times superior object detection and/or recognition (ODR) function may be built from a set of Bayesian stumps. Bayesian stumps may be constructed for each feature and object class, and the ODR function may be constructed from the subset of Bayesian stumps that minimize Bayesian error for a particular object class. That is, Bayesian error may be utilized as a feature selection measure for the ODR function. Furthermore, Bayesian stumps may be efficiently implemented as lookup tables with entries corresponding to unequal intervals of feature histograms. Interval widths and entry values may be determined so as to minimize Bayesian error, yielding Bayesian stumps that are optimal in this respect.

REFERENCES:
patent: 6954544 (2005-10-01), Jepson et al.
patent: 7020337 (2006-03-01), Viola et al.
patent: 7162076 (2007-01-01), Liu
patent: 7194114 (2007-03-01), Schneiderman
patent: 7668346 (2010-02-01), Xiao et al.
patent: 7720284 (2010-05-01), Zhang et al.
patent: 2004/0179719 (2004-09-01), Chen et al.
patent: 2005/0036690 (2005-02-01), Zhou et al.
patent: 2005/0264658 (2005-12-01), Ray et al.
patent: 2006/0088207 (2006-04-01), Schneiderman
patent: 2006/0233422 (2006-10-01), Toyama
patent: 2007/0036414 (2007-02-01), Georgescu et al.
patent: 2008/0107341 (2008-05-01), Lu
patent: 2008/0219558 (2008-09-01), Lu et al.
patent: WO2005073896 (2005-08-01), None
Huang, et al., “Jensen-Shannon Boosting Learning for Object Recognition”, IEEE, 2005, pp. 1-6.
Javed, et al., “Online Detection and Classification of Moving Objects Using Progressively Improving Detectors”, retrieved on Apr. 17, 2007, at <<http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=1467336>>, IEEE, 2006, pp. 1.
Levi, et al., “Learning Object Detection From a Small Number of Examples: The Importance of Good Features”, IEEE, 2004, pp. 1-8.
Li, et al., “Boosting Local Feature Based Classifiers for Face Recognition”, retrieved on Apr. 17, 2007, <<http://ieeexplore.ieee.org/xpl/freeabs—all.jsp?arnumber=1384880>>, IEEE, 2006, pp. 1.
Luo, “Optimization Design of Cascaded Classifiers”, IEEE, 2005, pp. 1-6.
Nevatia, “Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors”, retrieved on Apr. 17, 2007, at <<http://ieeexplore.ieee.org/xpl/freeabs—all.jsp?arnumber=1541243>>, IEEE, 2006, pp. 1.
Osuna, et al., “Training Support Vector Machines: An Application to Face Detection”, Proceeding of CVPR, 1997, pp. 1-8.
Rissanen, et al., “Density Estimation by Stochastic Complexity”, IEEE, vol. 38, No. 2, 1992, pp. 315-323.
Rowley, et al., “Neural Networked-Based Face Detection”, IEEE, vol. 20, No. 1, 1998, pp. 23-38.
Schneiderman, “Learning a Restricted Bayesian Networked for Object Detection”, IEEE, 2004, pp. 1-8.
Sun, et al., “Automatic Cascade Training with Perturbation Bias”, IEEE, 2004, pp. 1-8.
Viola, et al., “Rapid Object Detection Using a Boosted Cascade of Simple Features”, Computer Vision and Pattern Recognition, 2001, pp. 1-9.
Xiao, et al., “Robust Multipose Face Detection in Images”, IEEE, vol. 14, No. 1, 2004, pp. 31-41.
Birge et al., “How many bins should be put in a regular histogram”, pre-publication copy, presented at the University of Paris on Apr. 2002, 22 pages, published in ESAIM: P&S, Feb. 2006, vol. 10, pp. 24-45.
Bourdev et al., “Robust Object Detection Via Soft Cascade”, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, California, Jun. 20-26, 2005, vol. 2, pp. 236-253.
Brubacker et al., “Towards Optimal Training of Cascade Detectors”, 9th European Conference on Computer Vision (ECCV'06), Graz, Austria, May 7-13, 2006, 13 pages.
Huang et al., “Boosting Nested Cascade Detector for Multi-View Face Detection”, 17th International Conference on Pattern Recognition (ICPR'04), Cambridge, United Kingdom, Aug. 23-26, 2004, vol. 2, pp. 415-418.
Huang et al., “Jensen-Shannon Boosting Learning for Object Recognition”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, California, Jun. 20-26, 2005, vol. 2, pp. 144-149.
Javed et al., “Online Detection and Classification of Moving Objects Using Progressively Improving Detectors”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, California, Jun. 20-25, 2005, vol. 1, pp. 696-701.
Leinhart et al., “An Extended Set of Haar-like Features for Rapid Object Detection”, IEEE International Conference on Image Processing (ICIP'02), Rochester, NY, Sep. 22-25, 2002, vol. 1, pp. 900-903.
Levi et al., “Learning Object Detection From a Small Number of Examples: The Importance of Good Features”, IEEE Computer Science Conference on Computer Vision and Pattern Recognition (CVPR'04), Washington, DC, Jun. 27-Jul. 2, 2004, vol. 2, pp. 43-60.
Luo, “Optimization Design of Cascaded Classifiers”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, California, Jun. 20-26, 2005, vol. 1, pp. 480-485.
Osuna et al., “Training Support Vector Machines: An Application to Face Detection”, Conference on Computer Vision and Pattern Recognition (CVPR'97), San Juan, Puerto Rico, Jun. 17-19, 1997, 8 pages.
Rissanen et al., “Density Estimation by Stochastic Complexity”, IEEE Transactions on Information Theory, vol. 38, No. 2, Mar. 1992, pp. 315-323.
Rowley et al., “Neural Networked-Based Face Detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, No. 1, Jan. 1998, pp. 23-38.
Schapire et al., “Improved Boosting Algorithms Using Confidence-rated Predictions”, Machine Learning, vol. 37, No. 3, 1999, pp. 297-336.
Schneiderman, “Learning a Restricted Bayesian Network for Object Detection”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04), vol. 2, Washington, DC, Jun. 27-Jul. 2, 2004, 8 pages.
Sun et al., “Automatic Cascade Training with Perturbation Bias”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04), vol. 2, Washington, DC, Jun. 27-Jul. 2, 2004, 8 pages.
Viola et al., “Rapid Object Detection Using a Boosted Cascade of Simple Features”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'01), vol. 1, Kauai, Hawaii, Dec. 8-14, 2001, 9 pages.
Viola, et al., “Robust Real-time Object Detection”, Second International Workshop on Statistical and Computational Theories of Vision—Modeling, Learning, Computing, and Sampling, Vancouver, Canada, Jul. 13, 2001, 25 pages.
Wu et al., Abstract: “Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors”, Tenth IEEE International Conference on Computer Vision, vol. 1, Oct. 2005, 1 page, retrieved on Apr. 17, 2007, at <<http://ieeexplore.ieee.org/xpl/freeabs—all.jsp?arnumber=1541243>>.
Xiao et al., “Boosting Chain Learning for Object Detection”, Ninth IEEE International Conference on Computer Vision (ICCV'03), vol. 1, Nice, France, Oct. 13-16, 2003, 7 pages.
Xiao et al., “Robust Multipose Face Detection in Images”, IEEE Transactiona on Circuits and Systems for Video Technology, vol. 14, No. 1, Jan. 2004, pp. 31-41.
Zhang et al., “Boosting Local Feature Based Classifiers for Face Recognition”, Conference on Computer Vision and Pattern Recognition (CVPR'04), Washington, DC, Jun. 27-Jul. 2, 2004, vol. 5, pp. 87.

Affiliated with

Also associated with

Rating

Object detection and recognition with bayesian boosting does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object detection and recognition with bayesian boosting, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object detection and recognition with bayesian boosting will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2672940