Image analysis – Learning systems – Trainable classifiers or pattern recognizers
Reexamination Certificate
2007-12-04
2007-12-04
Mehta, Bhavesh M (Department: 2624)
Image analysis
Learning systems
Trainable classifiers or pattern recognizers
Reexamination Certificate
active
10217887
ABSTRACT:
The present invention recites a method and computer program product for identifying and correcting systematic noise in a pattern recognition classifier. A plurality of input patterns that have been determined not to be associated with any of a set of at least one represented output class are rejected by the pattern recognition classifier. A subset of pattern samples is selected from the rejected input patterns based upon the similarity of each pattern to one of the represented output classes. The selected pattern samples are subjected to an independent review to determine if they were correctly rejected. The classifier is retrained based upon this independent review of the selected pattern samples.
REFERENCES:
patent: 4451929 (1984-05-01), Yoshida
patent: 4475234 (1984-10-01), Nishijima et al.
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5060279 (1991-10-01), Crawford et al.
patent: 5265192 (1993-11-01), McCormack
patent: 5396565 (1995-03-01), Asogawa
patent: 5455892 (1995-10-01), Minot et al.
patent: 5561718 (1996-10-01), Trew et al.
patent: 5583968 (1996-12-01), Trompf
patent: 5712922 (1998-01-01), Loewenthal et al.
patent: 5719692 (1998-02-01), Cohen
patent: 6847731 (2005-01-01), Caulfield
patent: 2004/0205482 (2004-10-01), Basu et al.
Sarawagi, Sunita, Bhamidipaty, Anuradha. “Interactive Deduplication using Active Learning.” Proceedings of the 8thACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2002), ACM Jul. 2002.
Cullen, Mark, Pintsov, Leon, Romansky, Brian. “Reading Encrypted Postal Indicia.” IEEE 1995.
Ii David L.
Reitz, II Elliott D.
Tillotson Dennis A.
Lockheed Martin Corporation
Mehta Bhavesh M
Schaffer Jonathan
Tarolli, Sundheim Covell & Tummino LLP
LandOfFree
Method and computer program product for identifying and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and computer program product for identifying and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and computer program product for identifying and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3827768