Image analysis – Pattern recognition
Reexamination Certificate
2011-03-01
2011-03-01
Hung, Yubin (Department: 2624)
Image analysis
Pattern recognition
C382S187000
Reexamination Certificate
active
07899251
ABSTRACT:
Various technologies and techniques are disclosed that improve handwriting recognition operations. A balancing factor is calculated that can be used in recognition mode to compare out-of-dictionary recognition scores with in-dictionary recognition scores. Correct ink samples of words are provided, with some in-dictionary and some out-of-dictionary words. One or more tuning sets are generated from the samples, the tuning set(s) having a percentage of out-of-dictionary words based upon what is expected for a typical user. A handwriting recognizer is run against the tuning set(s) to determine statistics. The statistics are based upon the recognized answer for each word compared to the correct answer. The statistics are used to calculate the balancing factor. During recognition mode, a user inputs handwriting to be recognized. The balancing factor is used to compare and combine an in-dictionary alternate list with an out-of-dictionary alternate list to reach a recognition decision.
REFERENCES:
patent: 3651459 (1972-03-01), Hahn
patent: 5644648 (1997-07-01), Bose et al.
patent: 5680511 (1997-10-01), Baker et al.
patent: 5710866 (1998-01-01), Alleva et al.
patent: 5812697 (1998-09-01), Sakai et al.
patent: 5812698 (1998-09-01), Platt et al.
patent: 5903668 (1999-05-01), Beernink
patent: 5999902 (1999-12-01), Scahill et al.
patent: 6055333 (2000-04-01), Guzik et al.
patent: 6223155 (2001-04-01), Bayya
patent: 6393395 (2002-05-01), Guha et al.
patent: 6453070 (2002-09-01), Seni et al.
patent: 6633672 (2003-10-01), Guzik et al.
patent: 6677932 (2004-01-01), Westerman
patent: 6718060 (2004-04-01), Yokota et al.
patent: 6724936 (2004-04-01), Riemer
patent: 6735562 (2004-05-01), Zhang et al.
patent: 6850885 (2005-02-01), Raddino et al.
patent: 6970877 (2005-11-01), Rowley et al.
patent: 7158678 (2007-01-01), Nagel et al.
patent: 7228275 (2007-06-01), Endo et al.
patent: 7293231 (2007-11-01), Gunn et al.
patent: 7336827 (2008-02-01), Geiger et al.
patent: 7421417 (2008-09-01), Mangasarian et al.
patent: 2001/0018654 (2001-08-01), Hon et al.
patent: 2003/0007018 (2003-01-01), Seni et al.
patent: 2003/0086612 (2003-05-01), Hullender
patent: 2003/0110038 (2003-06-01), Sharma et al.
patent: 2004/0002940 (2004-01-01), Meek et al.
patent: 2004/0002986 (2004-01-01), Rowley et al.
patent: 2004/0006468 (2004-01-01), Gupta et al.
patent: 2004/0140956 (2004-07-01), Kushler et al.
patent: 2005/0049985 (2005-03-01), Mangasarian et al.
patent: 2005/0074169 (2005-04-01), Filatov et al.
patent: 2005/0129313 (2005-06-01), Hullender
patent: 2005/0256712 (2005-11-01), Yamada et al.
patent: 2005/0289140 (2005-12-01), Ford et al.
patent: 2006/0020461 (2006-01-01), Ogawa
patent: 2006/0190259 (2006-08-01), Jeong et al.
patent: 2007/0005356 (2007-01-01), Perronnin
patent: 2007/0005537 (2007-01-01), Abdulkader et al.
patent: 2007/0050191 (2007-03-01), Weider et al.
patent: 2008/0215301 (2008-09-01), Eyal et al.
patent: 2009/0276705 (2009-11-01), Ozdemir et al.
Yaeger et al., “Combining Neural Networks and Context-Driven Search for On-Line, Printed Handwriting Recognition in the Newton”, 1998, http://www.beanblossom.in.us/larryy/Yaegeretal.AlMag.pdf.
Safabakhsh et al., “Nastaaligh Handwritten Word Recognition Using a Continuous-Density Variable-Duration Hmm”, Apr. 2005, vol. 30, http://www.kfupm.edu.sa/publications/ajse/articles/301B—07P.pdf.
Hung Yubin
Microsoft Corporation
Yentrapati Avinash
LandOfFree
Balancing out-of-dictionary and in-dictionary recognition... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Balancing out-of-dictionary and in-dictionary recognition..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Balancing out-of-dictionary and in-dictionary recognition... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2701431