US5199084A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Apparatus and method for locating characters on a label
Assignee: International Business Machines Corp
•
Filing: 1991-08-16
•
Granted: 1993-03-30
•
Expires: 2011-08-16
Abstract
Abstract Locating and recognizing characters on a machine produced label, for example, is accomplished faster and more accurately by searching for first and second identifiable objects within first and second search windows, respectively. The first and second search windows are typically much smaller than the label or image being searched. The first object is the top portion of the label and the second object is the bottom portion of the label. Having located each object, a reference point is determined on each. From these two reference points, precise character or bar code locations can be predicted for reading the characters or bar codes printed on the label at predetermined locations. A character search window superimposed over each character at its estimated location is searched to read the character located thereat. If the first or second object could not be located, due to a torn label for example, an alternate object may be searched and a reference point located thereon.
Inventors
- 👤 Gregory T. Kishi
- 👤 Michael P. McIntosh
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 09:14
CPC Classifications
G; G06; G06K; G06K7/00; G06K7/10; G06K7/10544; G06K7/10821; G06K7/10861; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/146; G06K2207/00; G06K2207/1012
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
172 words
A method for efficiently locating an optically recognizable character encoded on a label, comprising machine-executed steps of: locating the label; searching in a first predetermined window for identifying a first predetermined object; determining a first reference mark position on the first predetermined object; searching in a second predetermined window for identifying a second predetermined object; determining a second reference mark position on the second predetermined object; calculating a first character window location relative to the first and second reference mark positions; reading a first character located within the first character window; and if the reading step failed: searching the first predetermined window for identifying a third predetermined object; determining a third reference mark position on the third predetermined object; searching the second predetermined window for identifying a fourth predetermined object; determining a fourth reference mark position on the fourth predetermined object; calculating the location of the first character window, the location being relative to the third and fourth reference mark positions; and reading the first character located within the first character window.
Claim 2
Independent Claim
172 words
A method for efficiently locating an optically recognizable character encoded on a label, comprising machine-executed steps of: locating the label; searching in a first predetermined window for identifying a first predetermined object; determining a first reference mark position on the first predetermined object; searching in a second predetermined window for identifying a second predetermined object; determining a second reference mark position on the second predetermined object; calculating a first character window location relative to the first and second reference mark positions; reading a first character located within the first character window; and if the reading step failed: searching the first predetermined window for identifying a third predetermined object; determining a third reference mark position on the third predetermined object; searching the second predetermined window for identifying a fourth predetermined object; determining a fourth reference mark position on the fourth predetermined object; calculating the location of the first character window, the location being relative to the third and fourth reference mark positions; and reading the first character located within the first character window.
Claim 3
Independent Claim
172 words
A method of efficiently locating an optically recognizable character encoded on a label, comprising machine-executed steps of: locating the label; searching in a first predetermined window for identifying a first predetermined object; determining a first reference mark position on the first predetermined object; searching in a second predetermined window for identifying a second predetermined object; determining a second reference mark position on the second predetermined object; calculating a first character window location relative to the first and second reference mark positions; reading a first character located within the first character window; and if either searching step failed: searching the first predetermined window for identifying a third predetermined object; determining a third reference mark position on the third predetermined object; searching the second predetermined window for identifying a fourth predetermined object; determining a fourth reference mark position on the fourth predetermined object; calculating the location of the first character window, the location being relative to the third and fourth reference mark positions; and reading the first character located within the first character window.
Claim 4
Independent Claim
172 words
A method of efficiently locating an optically recognizable character encoded on a label, comprising machine-executed steps of: locating the label; searching in a first predetermined window for identifying a first predetermined object; determining a first reference mark position on the first predetermined object; searching in a second predetermined window for identifying a second predetermined object; determining a second reference mark position on the second predetermined object; calculating a first character window location relative to the first and second reference mark positions; reading a first character located within the first character window; and if either searching step failed: searching the first predetermined window for identifying a third predetermined object; determining a third reference mark position on the third predetermined object; searching the second predetermined window for identifying a fourth predetermined object; determining a fourth reference mark position on the fourth predetermined object; calculating the location of the first character window, the location being relative to the third and fourth reference mark positions; and reading the first character located within the first character window.
Claim 5
Dependent Claim
24 words
The method according to claim 2 further comprising the machine executed step of reporting a label as missing if no predetermined objects are identified.
Claim 6
Dependent Claim
259 words
A vision system for reading coded data on a label, wherein the time required to reach each one of the coded data is reduced by accurately predicting the location of each one of the coded data by first locating first and second references positioned on the label, said vision system comprising: a processor; a memory coupled to said processor; a camera coupled to said processor; wherein said processor comprises means for searching a first image window for identifying a first object, the first object being a first portion of the label; means for searching a second image window for identifying a second object, the second object being a second portion of the label; means for determining the first reference position on the first object and the second reference position on the second object; means for predicting a first coded data window location, the location being relative to the first and second reference positions; means for instructing said processor to read the coded data; means for searching a third image window for identifying a third object if said camera failed to find the first or second object, the third object being a third portion of the label; means for searching a fourth image window for identifying a fourth object, the fourth object being a fourth portion of the label; means for determining a third reference position on the third object and a fourth reference position on the fourth object; and means for predicting the first coded data window location, the location being relative to the third and fourth reference positions.
Claim 7
Dependent Claim
259 words
A vision system for reading coded data on a label, wherein the time required to reach each one of the coded data is reduced by accurately predicting the location of each one of the coded data by first locating first and second references positioned on the label, said vision system comprising: a processor; a memory coupled to said processor; a camera coupled to said processor; wherein said processor comprises means for searching a first image window for identifying a first object, the first object being a first portion of the label; means for searching a second image window for identifying a second object, the second object being a second portion of the label; means for determining the first reference position on the first object and the second reference position on the second object; means for predicting a first coded data window location, the location being relative to the first and second reference positions; means for instructing said processor to read the coded data; means for searching a third image window for identifying a third object if said camera failed to find the first or second object, the third object being a third portion of the label; means for searching a fourth image window for identifying a fourth object, the fourth object being a fourth portion of the label; means for determining a third reference position on the third object and a fourth reference position on the fourth object; and means for predicting the first coded data window location, the location being relative to the third and fourth reference positions.
Claim 8
Dependent Claim
30 words
The vision system according to claim 4 wherein said processor further comprises means for indicating that the label is missing if the processor fails to locate any of the objects.
Claim 9
Dependent Claim
16 words
The vision system according to claim 5 wherein the first coded data is an alpha-numeric character.
Claim 10
Dependent Claim
16 words
The vision system according to claim 5 wherein the first coded data is a bar code.
Claim 11
Dependent Claim
26 words
The vision system according to claim 5 wherein the label is a predetermined size and each of the coded data is located at a predetermined location.
Claim 12
Dependent Claim
223 words
A robotic vision system for reading coded data on a label, the label being attached to an article for identifying said article, wherein the time required to reach each one of the coded data on the label is reduced by accurately predicting the location of each one of the coded data on the label thereby reducing a size of each coded data search window, said robotic vision system comprising: a processor; a memory coupled to said processor; a camera coupled to said processor; wherein said processor comprises: means for searching a first image window for identifying a first object, the first object being a top portion of the label; means for searching a second image window for identifying a second object, the second object being a bottom portion of the label; means for determining a first reference position on the first object and a second reference position on the second object; means for predicting a first coded data window location for placing a first coded data window, the location being relative to the first and second reference positions; means for reading a first coded data; and means for searching the first and second image windows for third and fourth objects, respectively, if the processor failed to identify the first or second objects, or if the processor failed to read the first coded data.
Claim 13
Dependent Claim
223 words
A robotic vision system for reading coded data on a label, the label being attached to an article for identifying said article, wherein the time required to reach each one of the coded data on the label is reduced by accurately predicting the location of each one of the coded data on the label thereby reducing a size of each coded data search window, said robotic vision system comprising: a processor; a memory coupled to said processor; a camera coupled to said processor; wherein said processor comprises: means for searching a first image window for identifying a first object, the first object being a top portion of the label; means for searching a second image window for identifying a second object, the second object being a bottom portion of the label; means for determining a first reference position on the first object and a second reference position on the second object; means for predicting a first coded data window location for placing a first coded data window, the location being relative to the first and second reference positions; means for reading a first coded data; and means for searching the first and second image windows for third and fourth objects, respectively, if the processor failed to identify the first or second objects, or if the processor failed to read the first coded data.
Claim 14
Dependent Claim
23 words
The robotic vision system according to claim 9 wherein the third and fourth objects are top and bottom corners, respectively, of the label.
Claim 15
Dependent Claim
32 words
The robotic vision system according to claim 10 wherein said processor further comprises means for indicating that the label is missing if the processor fails to locate the third and fourth objects.
Claim 16
Dependent Claim
17 words
The robotic vision system according to claim 9 wherein the first coded data is an alpha-numeric character.
Claim 17
Dependent Claim
17 words
The robotic vision system according to claim 9 wherein the first coded data is a bar code.
Claim 18
Dependent Claim
27 words
The robotic vision system according to claim 9 wherein the label is a predetermined size and each of the coded data is located at a predetermined location.
Claim 19
Dependent Claim
203 words
A subsystem for controlling a robotic vision system for reading coded data on a label, wherein the time required to read each one of the coded data on the label is reduced by accurately predicting the location of each one of the coded data on the label thereby reducing a size of each coded data search window, said subsystem comprising: storage means; a processor comprising: means for searching a first image window for identifying a first object, the first object being another portion of the label; means for searching a second image window for identifying a second object, the second object being another portion of the label; means for determining a first reference position on the first object and a second reference position on the second object; means for predicting a first coded data window location for placing a first coded data window, the location being relative to the first and second reference positions; means for reading the coded data within the first coded data window; and means for searching the first end second image windows for third and fourth objects, respectively, if the processor failed to identify the first or second objects, or if the processor failed to read the coded data.
Claim 20
Dependent Claim
203 words
A subsystem for controlling a robotic vision system for reading coded data on a label, wherein the time required to read each one of the coded data on the label is reduced by accurately predicting the location of each one of the coded data on the label thereby reducing a size of each coded data search window, said subsystem comprising: storage means; a processor comprising: means for searching a first image window for identifying a first object, the first object being another portion of the label; means for searching a second image window for identifying a second object, the second object being another portion of the label; means for determining a first reference position on the first object and a second reference position on the second object; means for predicting a first coded data window location for placing a first coded data window, the location being relative to the first and second reference positions; means for reading the coded data within the first coded data window; and means for searching the first end second image windows for third and fourth objects, respectively, if the processor failed to identify the first or second objects, or if the processor failed to read the coded data.
Claim 21
Dependent Claim
22 words
The program product according to claim 15 wherein the third and fourth objects are top and bottom corners, respectively, of the label.
Claim 22
Dependent Claim
31 words
The program product according to claim 16 wherein said processor further comprises means for indicating that the label is missing if the processor fails to locate the third or fourth objects.
Claim 23
Dependent Claim
26 words
The program product according to claim 17 wherein the label is a predetermined size and each of the coded data is located at a predetermined location.
References Cited (Backward Citations)
US3058093A
Cited
US3200373A
Cited
US3852715A
Cited
US3801775A
Cited
US4516265A
Cited
US4855981A
Cited
US4760247A
Cited
US4736109A
Cited
US4822986A
Cited
US4809344A
Cited
US4926492A
Cited
US4916298A
Cited
US4948955A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-03-29 | 1996-09-28 | 1997-03-30 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-03-29 | 2000-09-28 | 2001-03-30 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-03-29 | 2004-09-28 | 2005-03-30 | $7700.00 | Window Closed / Lapsed |