Accelerating the boosting approach to training classifiers

Image analysis – Learning systems – Trainable classifiers or pattern recognizers

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C382S156000, C382S170000, C382S224000, C706S006000, C706S020000

Reexamination Certificate

active

07421114

ABSTRACT:
Systems, methods, and computer program products implementing techniques for training classifiers. The techniques include receiving a training set that includes positive images and negative images, receiving a restricted set of linear operators, and using a boosting process to train a classifier to discriminate between the positive and negative images. The boosting process is an iterative process. The iterations include a first iteration where a classifier is trained by (1) testing some, but not all linear operators in the restricted set against a weighted version of the training set, (2) selecting for use by the classifier the linear operator with the lowest error rate, and (3) generating a re-weighted version of the training set. The iterations also include subsequent iterations during which another classifier is trained by repeating steps (1), (2), and (3), but using in step (1) the re-weighted version of the training set generated during a previous iteration.

REFERENCES:
patent: 7076473 (2006-07-01), Moghaddam
patent: 7286707 (2007-10-01), Liu et al.
patent: 2003/0110147 (2003-06-01), Li et al.
patent: 2004/0066966 (2004-04-01), Schneiderman
patent: 2004/0186816 (2004-09-01), Lienhart et al.
patent: 2005/0102246 (2005-05-01), Movellan et al.
patent: 2006/0062451 (2006-03-01), Li et al.
patent: 2006/0147107 (2006-07-01), Zhang et al.
patent: 2006/0222239 (2006-10-01), Bargeron et al.
patent: 2006/0248029 (2006-11-01), Liu et al.
patent: 2006/0269157 (2006-11-01), Eruhimov et al.
patent: 2007/0101269 (2007-05-01), Hua et al.
patent: 2007/0110308 (2007-05-01), Hwang et al.
Rob Schapire, “The Boosting Approach to Machine Learning,” Princeton University, www.cs.princeton.edu/˜schapire , 32 pages, 2002.
Paul Viola et al., “Robust Real-time Object Detection,” Compaq, Cambridge Research Laboratory, Technical Report Series, CRL 2001/01, 30 pages, Feb. 2001.
Ron Meir et al., “An Introduction to Boosting and Leveraging,” Dept. of Electrical Engineering, Technion, Haifa 3200, Israel, Research School of Information Sciences & Engineering, http://www-ee.technion.ac.il/˜rmeir, (66 pages), 2003.
Yoav Freund et al., “A Decision-TheoreticGeneralization of On-Line Learning and an Application to Boosting,”Journal of Computer and System Sciences, 55:119-139, (1997),Article No. SS971504.
Yang, Ming-Hsuan, et al., “Detecting Faces in Images: A Survey, ” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, No. 1, Jan. 2002, 25 pages.
Duda, Richard O., et al., “Pattern Classification and Scene Analysis,” John Wiley & Sons, Inc., © 1973, ISBN 0-471-22361-1,the entire book.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Accelerating the boosting approach to training classifiers does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Accelerating the boosting approach to training classifiers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accelerating the boosting approach to training classifiers will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3990649

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.