Techniques for filtering handwriting recognition results

Various technologies and techniques are disclosed that identify possible incorrect recognition results. Handwritten input is received from a user. A recognition operation is performed on the handwritten input to produce an initial recognition result. A possible incorrect recognition is identified us...

Full description

Saved in:
Bibliographic Details
Main Author Revow, Michael
Format Patent
LanguageEnglish
Published 08.06.2010
Online AccessGet full text

Cover

Abstract Various technologies and techniques are disclosed that identify possible incorrect recognition results. Handwritten input is received from a user. A recognition operation is performed on the handwritten input to produce an initial recognition result. A possible incorrect recognition is identified using the self-consistency process that identifies the possible incorrect recognition when the initial recognition result is not consistent with a normal writing style of the user. The self-consistency process performs a comparison of the initial recognition result with at least one sample previously provided by the user. If the comparison reveals that the initial recognition result is not consistent with the at least one sample, then the result is identified as possibly incorrect. A classifier confidence process can be alternatively or additionally used to identify a possible incorrect recognition result. The user interface for displaying the final result can be modified as appropriate given the possible incorrect recognition result.
AbstractList Various technologies and techniques are disclosed that identify possible incorrect recognition results. Handwritten input is received from a user. A recognition operation is performed on the handwritten input to produce an initial recognition result. A possible incorrect recognition is identified using the self-consistency process that identifies the possible incorrect recognition when the initial recognition result is not consistent with a normal writing style of the user. The self-consistency process performs a comparison of the initial recognition result with at least one sample previously provided by the user. If the comparison reveals that the initial recognition result is not consistent with the at least one sample, then the result is identified as possibly incorrect. A classifier confidence process can be alternatively or additionally used to identify a possible incorrect recognition result. The user interface for displaying the final result can be modified as appropriate given the possible incorrect recognition result.
Author Revow, Michael
Author_xml – sequence: 1
  givenname: Michael
  surname: Revow
  fullname: Revow, Michael
BookMark eNrjYmDJy89L5WSwCElNzsjLLCxNLVZIyy9SSMvMKUktysxLV8hIzEspL8osAbGLUpPz0_OA7Pw8ILu4NKekmIeBNS0xpziVF0pzMyi4uYY4e-iWFhcklqTmlRTHpxclgigDc3NjEwNLE2MilAAAPzgx5Q
ContentType Patent
CorporateAuthor Microsoft Corporation
CorporateAuthor_xml – name: Microsoft Corporation
DBID EFH
DatabaseName USPTO Issued Patents
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EFH
  name: USPTO Issued Patents
  url: http://www.uspto.gov/patft/index.html
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 07734094
GroupedDBID EFH
ID FETCH-uspatents_grants_077340943
IEDL.DBID EFH
IngestDate Sun Mar 05 22:42:56 EST 2023
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-uspatents_grants_077340943
OpenAccessLink https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7734094
ParticipantIDs uspatents_grants_07734094
PatentNumber 7734094
PublicationCentury 2000
PublicationDate 20100608
PublicationDateYYYYMMDD 2010-06-08
PublicationDate_xml – month: 06
  year: 2010
  text: 20100608
  day: 08
PublicationDecade 2010
PublicationYear 2010
References Oh, Jong, "An On-Line Handwriting Recognizer with Fisher Matching, Hypotheses Propagation Network and Context Constraint Models","May 2001", http://www.cs.nyu.edu/web/Research.
Thiesson et al. (2004/0234128) 20041100
Bennett et al. (7003158) 20060200
Ellozy et al. (5005205) 19910400
Tappert (4731857) 19880300
Sakai et al. (5812697) 19980900
Rieman (2005/0249419) 20051100
Parthasarathy (5742705) 19980400
Ehsani et al. (5917942) 19990600
Bennett et al. (7200267) 20070400
Nathan et al. (6256410) 20010700
Mankoff, Jennifer et al., "Providing Integrated Toolkit-Level Support for Ambiguity in Recognition-based Interfaces", CHI 2000 CHI Letters, vol. 2, Issue 1, Apr. 1-6, 2000, pp. 368-375.
Adcock (5764797) 19980600
(2005-141329) 20050600
Higgins et al. (5805710) 19980900
Nathan et al. (6567548) 20030500
Hoffberg et al. (5920477) 19990700
Lossev et al. (2004/0213455) 20041000
Beernink et al. (5666438) 19970900
Jojic et al. (2004/0095374) 20040500
International Search Report, PCT/US2007/013534, Oct. 30, 2007, pp. 1-9.
Chefalas et al. (5544260) 19960800
Aksela et al., "Methods for adaptive combination of classifiers with application to recognition of handwritten characters", International Journal on Document Analysis and Recognition (2003) 6:23-41.
Sanchez, Gomez E., "On-Line Character Analysis and Recognition with Fuzzy Neural Networks" http://ulises.tel.uva.es/uploaded-files/paper5.pdf.
Drissman, Avi, et al.,"Handwriting Recognition Systems: An Overview","Feb. 26, 1997", http://www.drissman.com/avi/school/HandwritingRecognition.pdf.
References_xml – year: 19980400
  ident: 5742705
  contributor:
    fullname: Parthasarathy
– year: 20051100
  ident: 2005/0249419
  contributor:
    fullname: Rieman
– year: 19980900
  ident: 5812697
  contributor:
    fullname: Sakai et al.
– year: 20010700
  ident: 6256410
  contributor:
    fullname: Nathan et al.
– year: 19980900
  ident: 5805710
  contributor:
    fullname: Higgins et al.
– year: 19970900
  ident: 5666438
  contributor:
    fullname: Beernink et al.
– year: 19910400
  ident: 5005205
  contributor:
    fullname: Ellozy et al.
– year: 20070400
  ident: 7200267
  contributor:
    fullname: Bennett et al.
– year: 20041100
  ident: 2004/0234128
  contributor:
    fullname: Thiesson et al.
– year: 20041000
  ident: 2004/0213455
  contributor:
    fullname: Lossev et al.
– year: 19990600
  ident: 5917942
  contributor:
    fullname: Ehsani et al.
– year: 20030500
  ident: 6567548
  contributor:
    fullname: Nathan et al.
– year: 19990700
  ident: 5920477
  contributor:
    fullname: Hoffberg et al.
– year: 19880300
  ident: 4731857
  contributor:
    fullname: Tappert
– year: 20060200
  ident: 7003158
  contributor:
    fullname: Bennett et al.
– year: 19960800
  ident: 5544260
  contributor:
    fullname: Chefalas et al.
– year: 20040500
  ident: 2004/0095374
  contributor:
    fullname: Jojic et al.
– year: 20050600
  ident: 2005-141329
– year: 19980600
  ident: 5764797
  contributor:
    fullname: Adcock
Score 2.7759783
Snippet Various technologies and techniques are disclosed that identify possible incorrect recognition results. Handwritten input is received from a user. A...
SourceID uspatents
SourceType Open Access Repository
Title Techniques for filtering handwriting recognition results
URI https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7734094
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED-2IahPiorzizz4Gm2XLonPslIEZQ8T9jbSNBFhpmNJ2b-_S6vFF307ErgcFy53l7v8AnCvSsW1TS1V8SPAzBi0Oa0tBnK24lyJTLZ_Eby-8eI9e1lOlwMo-rcwX2hGdIOy-IfGb0LdNlfi8d5tPO3AnyNGoIvoAzu3rlU1r-yjECymKkMYyiS29s3y4hgOkQWGbC74X04jP4GDeTt6CgPjzkAufuBSPcFIkdjPWKhGz0Hi5fUuggsh3Tf01A5p36yDPweSzxbPBe2XWX1sY_vKKvkWh13ACNN4cwlk8pQYzKY4KmeaVaUuxUSnTDCrU6mYSMcw_pPN1T9z13DUVbQ5TeQNjMK2MbfoKEN512phDzHYdWI
link.rule.ids 230,309,783,805,888,64367
linkProvider USPTO
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDLbGQDxOIECMZw9cA-3aJd0ZqMpr6mFIu1VpmiCkLZ2WVvv7OCmruMDNSiTHcuTYjp0vALe84FSoQBFuPwKMpESbE0JhIKdKSjmLYvcXwfuEph_Ry2w060HavYVZoBmRJcpi7hqzrCvXXInHe7vxpAV_thiB2qIPrPW84mVWqnvGQpuqbME2-ljqUrIkPYA9ZIJBm67NL7eRHMJO5kaPoCf1McTTDWCq8TBW9NSXLVWj7_Ds9fXawgsh3bX0VBpp08xrcwJe8jR9SEm3TP65sg0suf8jUHgKfUzk5Rl4w7EvMZ-iqJ5RVBaiYEMRhCxUIoh5yIIBDP5kc_7P3A3sZo9J_vY8eb2A_ba8TYkfX0K_XjXyCr1mXVw7hXwDIDV4Xw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Techniques+for+filtering+handwriting+recognition+results&rft.inventor=Revow%2C+Michael&rft.number=7734094&rft.date=2010-06-08&rft.externalDBID=n%2Fa&rft.externalDocID=07734094