Flexible MQDF classifier model compression

Details Flexible MQDF classifier model compression Flexible MQDF classifier model compression

2011-07-05

2011-07-05

Mehta, Bhavesh M (Department: 2624)

Image analysis

Pattern recognition

Classification

C382S185000, C382S186000

Reexamination Certificate

active

07974476

ABSTRACT:
A memory footprint of an Modified Quadratic Discriminant Function (MQDF) pattern recognition classifier is reduced without resulting in unacceptable classification accuracy degradation. Covariance matrices for multiple classes are clustered into a smaller number of matrices where different classes share the same set of eigenvectors. According to another approach, different numbers of principal components are stored for different classes based on criteria such as class usage frequency, larger variation in writing, and the like, resulting in fewer principal components to be stored in memory.

REFERENCES:
patent: 4155072 (1979-05-01), Kawa
patent: 5602938 (1997-02-01), Akiyama et al.
patent: 5854855 (1998-12-01), Errico et al.
patent: 6345109 (2002-02-01), Souma et al.
patent: 6721452 (2004-04-01), Confer et al.
patent: 7031530 (2006-04-01), Driggs et al.
patent: 7181062 (2007-02-01), Ii et al.
patent: 2003/0169925 (2003-09-01), Polonowski
patent: 2009/0304296 (2009-12-01), Zhang et al.
Mitoma et al. (Sep. 2005) “Online character recognition based on elastic matching and quadratic discrimination.” Proc. 8th Int'l Conf. on Document Analysis and Recognition, pp. 36-40.
Kimura et al. (Jan. 1987) “Modified quadratic discriminant functions and the application to Chinese character recognition.” IEEE Trans on Pattern Analysis and Machine Intelligence, vol. PAMI-9, No. 1, pp. 149-153.
Liu, C., “Handwritten Chinese Character Recognition: Effects of Shape Normalization and Feature Extraction,” http://hal.inria.fr/docs/00/12/04/08/PDF/liama2.pdf, 15 pages (Publicly known at least as early as May 30, 2007).
Liu, C., “High Accuracy Handwritten Chinese Character Recognition Using Quadratic Classifiers with Discriminative Feature Extraction,” http://hal.inria.fr/docs/00/12/04/19/PDF/liama4.pdf, 4 pages (Copyright 2006).
Liu, H. et al., “Handwritten Character Recognition Using Gradient Feature and Quadratic Classifier with Multiple Discrimination Schemes,”Eighth International Conference on Document Analysis and Recognition, vol. 1, pp. 19-23 (Aug. 29-Sep. 1, 2005) (1 page Abstract).
Omachi, S. et al., “Precise Estimation of High-Dimensional Distribution and Its Application to Face Recognition,”Proceedings 17th Intenrational Conference on Pattern Recognition, http://www.tbgu.ac.jp/ait/fan/paper/icpr2004-1-220.pdf, 4 pages (Aug. 2004).

Affiliated with

Also associated with

Rating

Flexible MQDF classifier model compression does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Flexible MQDF classifier model compression, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Flexible MQDF classifier model compression will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2732896