Pattern feature selection method, classification method,...

Details Pattern feature selection method, classification method,... Pattern feature selection method, classification method,...

2003-02-27

2009-12-15

Kim, Charles (Department: 2624)

Image analysis

Pattern recognition

Classification

C382S159000, C382S290000

Reexamination Certificate

active

07634140

ABSTRACT:
Feature decision means (303) decides a set of features appropriate for pattern identification from a plenty of feature candidates generated by feature candidate generation means (302) by using learning patterns stored in learning, pattern storage means (301). The feature decision means (303) successively decides features according to a reference of information maximization under the condition that the decided feature is known while adding an effective noise to the learning pattern and performs information amount calculation approximately and at a high speed while merging the learning patterns into a set of N elements when required. As a result, it is possible to automatically create a feature set appropriate for pattern identification of a high performance without requiring enormous learning. Moreover, by using a transition table (305) containing transitions between sets, it is possible to perform pattern judgment with a high efficiency.

REFERENCES:
patent: 5497430 (1996-03-01), Sadovnik et al.
patent: 5675710 (1997-10-01), Lewis
patent: 6128608 (2000-10-01), Barnhill
patent: 6208758 (2001-03-01), Ono et al.
patent: 61-75486 (1986-04-01), None
patent: 63-79192 (1988-04-01), None
patent: 64-65680 (1989-03-01), None
patent: 1-321591 (1989-12-01), None
patent: 4-84277 (1992-03-01), None
patent: 4-112391 (1992-04-01), None
patent: 4-256087 (1992-09-01), None
patent: 5-108890 (1993-04-01), None
patent: 6-4673 (1994-01-01), None
patent: 6-251156 (1994-09-01), None
patent: 6-162198 (1996-09-01), None
patent: 9-245124 (1997-09-01), None
patent: 9-288492 (1997-10-01), None
patent: 9-305574 (1997-11-01), None
patent: 8-106295 (1998-05-01), None
patent: 10-320402 (1998-12-01), None
patent: 2000-122690 (2000-04-01), None
patent: 2001-34709 (2001-02-01), None
patent: WO 99/67728 (1999-12-01), None
patent: WO 01/31579 (2001-05-01), None
Battiti, Roberto, “Using Mutual Information for Selecting Features in Supervised Neural Net Learning”, 8357 IEEE Transactions on Neural Networks 5(1994) Jul., No. 4, New York, US, 1994.
“Optimal Feature Extraction by Visual Cortical Neurons” Okajima, NEC Fundamental Research Laboratories, p. 133-136, 1999.
“Neurocomputer” edited by Kaoru Nakamura, Gijutsu-Hyohron Co. Ltd. 1989.
“Parallel Distributed Processing” Rumelhart et al., MIT Press, pp. 317-329.
“C4.5: Programs for Machine Learning” Quinlan, 1993, pp. 17-25.

Affiliated with

Also associated with

Rating

Pattern feature selection method, classification method,... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Pattern feature selection method, classification method,..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern feature selection method, classification method,... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4079009