Patent US5212741A successfully refreshed from Google Patents.
US5212741A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Preprocessing of dot-matrix/ink-jet printed text for Optical Character Recognition
Assignee: Eastman Kodak Co
•
Filing: 1992-01-21
•
Granted: 1993-05-18
•
Expires: 2012-01-21
Abstract
Abstract Method and apparatus are disclosed for processing image data of dot-matrix/ink-jet printed text to perform Optical Character Recognition (OCR) of such image data. In the method and apparatus, the image data is viewed for detecting if dot-matrix/ink-jet printed text is present. Any detected dot-matrix/ink-jet produced text is then pre-processed by determining the image characteristic thereof by forming a histogram of pixel density values in the image data. A 2-D spatial averaging operation as a second pre-processing step smooths the dots of the characters into strokes and reduces the dynamic range of the image data. The resultant spatially averaged image data is then contrast stretched in a third pre-processing step to darken dark regions of the image data and lighten light regions of the image data. Edge enhancement is then applied to the contrast stretched image data in a fourth pre-processing step to bring out higher frequency line details. The edge enhanced image data is then binarized and applied to a dot-matrix/ink jet neural network classifier for recognizing characters in the binarized image data from a predetermined set of symbols prior to OCR.
Inventors
- 👤 Lori L. Barski
- 👤 Roger S. Gaborski
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 14:42
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/16; G06V30/162
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
118 words
A method of processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising the steps of: (a) determining the image characteristics of the dot-matrix/ink-jet image data by forming a histogram of density values of pixels of the image data; (b) reducing a dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes using a 2-D spatial averaging operation; (c) performing a contrast stretching operation on the altered structure of the characters produced in step (b); (d) performing edge enhancement of the characters of the image data produced in step (c); and (e) binarizing the edge enhanced image data of step (d).
Claim 2
Independent Claim
118 words
A method of processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising the steps of: (a) determining the image characteristics of the dot-matrix/ink-jet image data by forming a histogram of density values of pixels of the image data; (b) reducing a dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes using a 2-D spatial averaging operation; (c) performing a contrast stretching operation on the altered structure of the characters produced in step (b); (d) performing edge enhancement of the characters of the image data produced in step (c); and (e) binarizing the edge enhanced image data of step (d).
Claim 3
Dependent Claim
46 words
The method of claim 1 further comprising the steps of: (f) prior to performing step (a), detecting if dot-matrix or ink-jet printed text is present in the image data; and (g) sending all dot-matrix or ink-jet printed image data for processing by steps (a) to (e).
Claim 4
Dependent Claim
40 words
The method of claim 1 further comprising the step of: (f) processing the binarized image data of step (e) in a neural network classifier for recognizing characters in the image data from a predetermined set of symbols for subsequent OCR.
Claim 5
Dependent Claim
66 words
The method of claim 1 wherein in performing step (b), performing the substeps of: (b1) moving a predetermined NxN mask pixel-by-pixel across the image data, where N is an odd integer greater than 1; (b2) calculating an average density value of the NxN pixels overlaid by the mask; and (b3) replacing the central pixel overlaid by the NxN mask with an average of the NxN pixels.
Claim 6
Independent Claim
144 words
A method of processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising the sequential steps of: (a) detecting whether dot-matrix or ink-jet printed text is present in the image data; (b) determining the image characteristics of the dot-matrix/ink-jet image data detected in step (a) by forming a histogram of density values of pixels of the image data; (c) reducing a dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes using the histogram produced in step (b) and a 2-D spatial averaging operation; (d) performing a contrast stretching operation on the altered structure of the characters produced in step (c); (e) performing edge enhancement of the characters of the image data produced in step (d); and (f) binarizing the edge enhanced image data of step (e).
Claim 7
Independent Claim
144 words
A method of processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising the sequential steps of: (a) detecting whether dot-matrix or ink-jet printed text is present in the image data; (b) determining the image characteristics of the dot-matrix/ink-jet image data detected in step (a) by forming a histogram of density values of pixels of the image data; (c) reducing a dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes using the histogram produced in step (b) and a 2-D spatial averaging operation; (d) performing a contrast stretching operation on the altered structure of the characters produced in step (c); (e) performing edge enhancement of the characters of the image data produced in step (d); and (f) binarizing the edge enhanced image data of step (e).
Claim 8
Dependent Claim
41 words
The method of claim 5 further comprising the step of: (g) processing the binarized image data of step (f) in a neural network classifier for recognizing characters in the binarized image data from a predetermined set of symbols for subsequent OCR.
Claim 9
Dependent Claim
66 words
The method of claim 5 wherein in performing step (c), performing the substeps of: (c1) moving a predetermined NxN mask pixel-by-pixel across the image data, where N is an odd integer greater than 1; (c2) calculating an average density value of the NxN pixels overlaid by the mask; and (c3) replacing the central pixel overlaid by the NxN mask with an average of the NxN pixels.
Claim 10
Dependent Claim
148 words
Apparatus for processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising: pre-processing means for pre-processing the image data of the dot-matrix or ink-jet printed text comprising; (a) determining means for determining the image characteristics of the dot-matrix/ink-jet image data by forming a histogram of density values of pixels of the image data; (b) 2-D spatial averaging means for reducing the dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes; (c) contrast stretching means for performing a contrast stretching operation on the altered structure of the characters produced by the 2-D spatial averaging means; and (d) edge enhancement means for performing edge enhancement of the characters of the image data produced by the contrast stretching means; and binarizing means for binarizing the edge enhanced image data from the pre-processing means.
Claim 11
Dependent Claim
148 words
Apparatus for processing image data of dot-matrix-ink-jet printed text for Optical Character Recognition (OCR) comprising: pre-processing means for pre-processing the image data of the dot-matrix or ink-jet printed text comprising; (a) determining means for determining the image characteristics of the dot-matrix/ink-jet image data by forming a histogram of density values of pixels of the image data; (b) 2-D spatial averaging means for reducing the dynamic range of the image data by altering the structure of characters in the image data from that of dots to one of strokes; (c) contrast stretching means for performing a contrast stretching operation on the altered structure of the characters produced by the 2-D spatial averaging means; and (d) edge enhancement means for performing edge enhancement of the characters of the image data produced by the contrast stretching means; and binarizing means for binarizing the edge enhanced image data from the pre-processing means.
Claim 12
Dependent Claim
41 words
The apparatus of claim 8 further comprising print detection means for detecting whether dot-matrix or ink-jet printed text is present in the image data and sending the image data to the determining means if the image data contains dot-matrix/ink-jet printed text.
Claim 13
Dependent Claim
38 words
The apparatus of claim 8 further comprising a neural network classifier for receiving the binarized image data from the binarizing means for recognizing characters in the binarized image data from a predetermined set of symbols for subsequent OCR.
Claim 14
Dependent Claim
66 words
The apparatus of claim 8 wherein the 2-D spatial averaging means comprises means for (a) moving a predetermined NxN mask pixel-by-pixel across the image data, where N is an odd integer greater than 1, (b) calculating an average density value of the NxN pixels overlaid by the mask, and (c) replacing the central pixel overlaid by the NxN mask with an average of the NxN pixels.
Claim 15
Dependent Claim
53 words
The apparatus of claim 8 wherein the pre-processing means is a central processor or microcomputer comprising: a processing unit; and a memory comprising memory locations for storing programs and data for permitting the processing unit to perform image characteristics calculations, 2-D spatial averaging, contrast stretching, and edge enhancement on the dot-matrix/ink-jet image data.
References Cited (Backward Citations)
US3196398A
Cited
US3289163A
Cited
US3737855A
Cited
US4074231A
Cited
USH461H
Cited
US4263504A
Cited
US4365304A
Cited
US4691366A
Cited
US4953114A
Cited
US4646355A
Cited
US4791679A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-05-17 | 1996-11-16 | 1997-05-18 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-05-17 | 2000-11-16 | 2001-05-18 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-05-17 | 2004-11-16 | 2005-05-18 | $7700.00 | Window Closed / Lapsed |