Image analysis – Learning systems – Trainable classifiers or pattern recognizers
Patent
1997-03-03
1999-10-12
Boudreau, Leo H.
Image analysis
Learning systems
Trainable classifiers or pattern recognizers
382155, 382156, 382157, 382158, 382161, 382187, 382224, 382227, G06K 962
Patent
active
059664606
ABSTRACT:
A neural network based improving the performance of an omni-font classifier by using recognized characters for additional training is presented. The invention applies the outputs of the hidden layer nodes of the neural net as the feature vector. Characters that are recognized with high confidence are used to dynamically train a secondary classifier. After the secondary classifier is trained, it is combined with the original main classifier. The invention can re-adjust the partition or boundary of feature space, based on on-line learning, by utilizing the secondary classifier data to form an alternative partition location. The new partition can be referred to when a character conflict exists during character recognition.
REFERENCES:
patent: 4551851 (1985-11-01), Kochert
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5212767 (1993-05-01), Higashino et al.
patent: 5214747 (1993-05-01), Cok
patent: 5222194 (1993-06-01), Nishimura
patent: 5239594 (1993-08-01), Yoda
patent: 5245697 (1993-09-01), Suzuoka
patent: 5337370 (1994-08-01), Gilles et al.
patent: 5418864 (1995-05-01), Murdock et al.
patent: 5528700 (1996-06-01), Takatori et al.
patent: 5542006 (1996-07-01), Shustorovich et al.
patent: 5590218 (1996-12-01), Ornstein
patent: 5638491 (1997-06-01), Moed
"Neural Nets for Computing", IEEE International Conference on Acoustics, Speech, and Signal Processing, 1981.
Fan Zhigang
Porter, III Gilbert B.
Roberts, Jr. Frederick J.
Blair Philip E.
Boudreau Leo H.
Cohen Gary B.
Patel Kanji
Xerox Corporation
LandOfFree
On-line learning for neural net-based character recognition syst does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with On-line learning for neural net-based character recognition syst, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On-line learning for neural net-based character recognition syst will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-659957