← Back to Patent Explorer
US5146512A Expired / Lapsed US ⏱️ 0.0 years remaining

Method and apparatus for utilizing multiple data fields for character recognition

Assignee: Bantec Inc
•
Filing: 1991-02-14
•
Granted: 1992-09-08
•
Expires: 2011-02-14
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A system (10) for recognizing numerical characters which appear as both numerical characters and words on a document includes an image capture device (12) for capturing the image of a document. A recognition circuit (14) performs recognition of the numerical characters. A recognition circuit (16) performs recognition of the words corresponding to the numerical characters. A comparator circuit (20) compares the recognition signals generated by the recognition circuit (16) to the recognition signals generated by the recognition circuit (14) to determine if the numerical characters recognized by the recognition circuit (14) is correct.

Inventors

  • 👤 William E. Weideman
  • 👤 Carl G. O'Connor

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-10-29 13:02
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/98; G06V10/987

Claims Analysis

Total Claims: 13
Claim 1
Independent Claim 222 words
A system for recognizing numerical characters of a numerical field of numerical characters which appears in both numerical characters and words on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the numerical characters of the numerical field and for generating a first set of recognition signals representing each of the numerical characters and including: means for storing feature sets representative of known numerical characters to form a reference data set; means for storing an image containing a plurality of unknown numerical characters; means for scanning said image containing said plurality of unknown numerical characters; means for segmenting said plurality of unknown numerical characters contained in said image; means for forming feature sets representative of each of said segmented unknown numerical characters; and means for comparing said reference data set with said feature sets of each of said segmented unknown numerical characters; second recognition means connected to said image capture means for recognizing the words representing the numerical characters and for generating a second set of recognition signals; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 2
Independent Claim 222 words
A system for recognizing numerical characters of a numerical field of numerical characters which appears in both numerical characters and words on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the numerical characters of the numerical field and for generating a first set of recognition signals representing each of the numerical characters and including: means for storing feature sets representative of known numerical characters to form a reference data set; means for storing an image containing a plurality of unknown numerical characters; means for scanning said image containing said plurality of unknown numerical characters; means for segmenting said plurality of unknown numerical characters contained in said image; means for forming feature sets representative of each of said segmented unknown numerical characters; and means for comparing said reference data set with said feature sets of each of said segmented unknown numerical characters; second recognition means connected to said image capture means for recognizing the words representing the numerical characters and for generating a second set of recognition signals; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 3
Dependent Claim 48 words
The system for recognizing numerical characters of a numerical field of numerical characters of claim 1 where said second recognition means includes: means for generating a numerical equivalent of the words for use in comparison to each of said recognition signals of said first set of recognition signals.
Claim 4
Independent Claim 206 words
A system for recognizing numerical characters of a numerical field of numerical characters which appears in both numerical characters and words on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the numerical characters of the numerical field and for generating a first set of recognition signals representing each of the numerical characters; second recognition means connected to said image capture means for recognizing the words representing the numerical characters and for generating a second set of recognition signals and including: means for storing feature sets representative of the known words to form a reference data set; means for storing an image containing a plurality of unknown words; means for segmenting said plurality of unknown words contained in said image; means for forming feature sets representative of each of said segmented unknown words; and means for comparing said reference data set with said feature sets of each of said segmented unknown words; and means connected to said first and second recognition means for comprising said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 5
Independent Claim 206 words
A system for recognizing numerical characters of a numerical field of numerical characters which appears in both numerical characters and words on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the numerical characters of the numerical field and for generating a first set of recognition signals representing each of the numerical characters; second recognition means connected to said image capture means for recognizing the words representing the numerical characters and for generating a second set of recognition signals and including: means for storing feature sets representative of the known words to form a reference data set; means for storing an image containing a plurality of unknown words; means for segmenting said plurality of unknown words contained in said image; means for forming feature sets representative of each of said segmented unknown words; and means for comparing said reference data set with said feature sets of each of said segmented unknown words; and means connected to said first and second recognition means for comprising said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 6
Dependent Claim 49 words
The system for recognizing numerical characters of a numerical field of numerical characters of claim 3 where said second recognition means further includes: means for generating a numerical equivalent of the words for use in comparison to each of said recognition signals of said first set of recognition signals.
Claim 7
Independent Claim 206 words
A system for recognizing words having an associated numerical field of numerical characters which appear on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the words and for generating a first set of recognition signals representing each of the words and including: means for storing feature sets representative of the known words to form a reference data set; means for storing an image containing a plurality of unknown words; means for scanning said image containing said plurality of unknown words; means for segmenting said plurality of unknown words contained in said image; means for forming feature sets representative of each of said segmented unknown words; and means for comparing said reference data set with said feature sets of each of said segmented unknown words; second recognition means connected to said image capture means for recognizing the numerical characters associated with the words and for generating a second set of recognition signals; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 8
Independent Claim 206 words
A system for recognizing words having an associated numerical field of numerical characters which appear on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the words and for generating a first set of recognition signals representing each of the words and including: means for storing feature sets representative of the known words to form a reference data set; means for storing an image containing a plurality of unknown words; means for scanning said image containing said plurality of unknown words; means for segmenting said plurality of unknown words contained in said image; means for forming feature sets representative of each of said segmented unknown words; and means for comparing said reference data set with said feature sets of each of said segmented unknown words; second recognition means connected to said image capture means for recognizing the numerical characters associated with the words and for generating a second set of recognition signals; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 9
Independent Claim 29 words
The system for recognizing means further includes; means for generating a numerical equivalent of the words for use in comparison of said first and second sets of recognition signals.
Claim 10
Independent Claim 29 words
The system for recognizing means further includes; means for generating a numerical equivalent of the words for use in comparison of said first and second sets of recognition signals.
Claim 11
Independent Claim 210 words
A system for recognizing words having an associated numerical field of numerical characters which appear on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the words and for generating a first set of recognition signals representing each of the words; second recognition means connected to said image capture means for recognizing the numerical characters associated with the words and for generating a second set of recognition signals and including: means for storing feature sets representative of know numerical characters to form a reference data set; means for storing an image containing a plurality of unknown numerical characters; means for scanning said image containing said plurality of unknown numerical characters; means for segmenting said plurality of unknown numerical characters contained in said image; means for forming feature sets representative of each of said segmented unknown numerical characters; and means for comparing said reference data set with said feature sets of each said segmented unknown numerical characters; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 12
Independent Claim 210 words
A system for recognizing words having an associated numerical field of numerical characters which appear on a document comprising: image capture means for capturing the image of the document; first recognition means connected to said image capture means for recognizing each of the words and for generating a first set of recognition signals representing each of the words; second recognition means connected to said image capture means for recognizing the numerical characters associated with the words and for generating a second set of recognition signals and including: means for storing feature sets representative of know numerical characters to form a reference data set; means for storing an image containing a plurality of unknown numerical characters; means for scanning said image containing said plurality of unknown numerical characters; means for segmenting said plurality of unknown numerical characters contained in said image; means for forming feature sets representative of each of said segmented unknown numerical characters; and means for comparing said reference data set with said feature sets of each said segmented unknown numerical characters; and means connected to said first and second recognition means for comparing said first and second sets of recognition signals to determine if each of said recognition signals of said first set of recognition signals is correct.
Claim 13
Dependent Claim 37 words
The system for recognizing words of claim 7 wherein said first recognition means further includes: means for generating a numerical equivalent of the words for use in comparison of said first and second sets of recognition signals.

References Cited (Backward Citations)

US3766520A Cited
US3842402A Cited
US3949363A Cited
US4020463A Cited
US4028674A Cited
US4201978A Cited
US4442541A Cited
US4524453A Cited
US4417136A Cited
US4563771A Cited
US4773099A Cited
US4754489A Cited
US4764973A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 1995-09-08 1996-03-09 1996-09-08 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 1999-09-08 2000-03-09 2000-09-08 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2003-09-08 2004-03-09 2004-09-08 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag