Image analysis – Pattern recognition – Limited to specially coded – human-readable characters
Reexamination Certificate
2006-11-15
2010-06-08
Mehta, Bhavesh M (Department: 2624)
Image analysis
Pattern recognition
Limited to specially coded, human-readable characters
C382S177000, C382S176000, C382S317000, C382S321000, C358S462000
Reexamination Certificate
active
07734092
ABSTRACT:
A method of processing an image includes receiving a digital version of the image, processing the digital version of the image through at least two binarization processes to thereby create a first binarization and a second binarization, and processing the first binarization through a first optical character recognition process to thereby create a first OCR output file. Processing the first binarization through a first optical character recognition process includes compiling first metrics associated with the first OCR output file. The method also includes processing the second binarization through the first optical character recognition process to thereby create a second OCR output file. Processing the second binarization through the first optical character recognition process includes compiling second metrics associated with the second OCR output file. The method also includes using the metrics, at least in part, to select a final OCR output file from among the OCR output files.
REFERENCES:
patent: 5519786 (1996-05-01), Courtney et al.
patent: 5617484 (1997-04-01), Wada et al.
patent: 5809167 (1998-09-01), Al-Hussein
patent: 5920655 (1999-07-01), Makita et al.
patent: 6269188 (2001-07-01), Jamali
patent: 6304313 (2001-10-01), Honma
patent: 6330003 (2001-12-01), Curtis et al.
patent: 6351566 (2002-02-01), Zlotnick
patent: 6438265 (2002-08-01), Heilper et al.
patent: 6571013 (2003-05-01), Macey et al.
patent: 6577762 (2003-06-01), Seeger et al.
patent: 6738496 (2004-05-01), Van Hall
patent: 6741351 (2004-05-01), Marshall et al.
patent: 6741745 (2004-05-01), Dance et al.
patent: 6868524 (2005-03-01), Fushiki et al.
patent: 6922487 (2005-07-01), Dance et al.
patent: 6947574 (2005-09-01), Graulich et al.
patent: 7236632 (2007-06-01), Erol et al.
patent: 7339992 (2008-03-01), Chang et al.
patent: 7403656 (2008-07-01), Koga
patent: 2001/0041005 (2001-11-01), Fujiwara
patent: 2002/0008715 (2002-01-01), Sorek et al.
patent: 2002/0015167 (2002-02-01), Watanabe et al.
patent: 2002/0015524 (2002-02-01), Fujiwara
patent: 2002/0021840 (2002-02-01), Ohara et al.
patent: 2002/0057838 (2002-05-01), Steger
patent: 2002/0067581 (2002-06-01), Hiramoto et al.
patent: 2002/0067851 (2002-06-01), Lange et al.
patent: 2002/0154134 (2002-10-01), Matsui
patent: 2003/0012440 (2003-01-01), Nakanishi et al.
patent: 2003/0113016 (2003-06-01), Naoi et al.
patent: 2004/0146200 (2004-07-01), Andel et al.
patent: 2005/0024679 (2005-02-01), Yoda et al.
patent: 2005/0031208 (2005-02-01), Ohara et al.
patent: 2005/0138555 (2005-06-01), Fushiki et al.
patent: 2005/0180632 (2005-08-01), Aradhye et al.
patent: 2005/0271294 (2005-12-01), Takahashi
patent: 2006/0039605 (2006-02-01), Koga
patent: 2007/0019881 (2007-01-01), Curtis
patent: 2007/0047816 (2007-03-01), Graham et al.
patent: 2007/0201757 (2007-08-01), Madej et al.
patent: 2007/0269139 (2007-11-01), Erol et al.
patent: 2008/0008383 (2008-01-01), Andel et al.
patent: 2008/0063279 (2008-03-01), Vincent et al.
patent: 2008/0170785 (2008-07-01), Simmons et al.
Definition—“Image Binarization”; www.haifa.ibm.com, pp. 1 of 1.
Merriam-Webster Online Dictionary-define metrics.
Gupta et al. OCR Binarization and image pre-processing for searching historical documents—Science Direct Pattern Recognition 20 (2007) 389-397.
Khashman et al Global Binarization of Document Images Using Neural Network—pp. 619-626 (1-8).
Thillou et al Segmentation Based Binarization for Color Degraded Images—Computer Vision and Graphics 2006 pp. 808-813.
Curtis Donald B.
Reid Shawn
Ancestry.com Operations Inc.
Mehta Bhavesh M
Thomas Mia M
Townsend and Townsend / and Crew LLP
LandOfFree
Multiple image input for optical character 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 Multiple image input for optical character recognition..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiple image input for optical character recognition... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4190079