Image analysis – Pattern recognition – Limited to specially coded – human-readable characters
Reexamination Certificate
1996-12-20
2002-04-02
Couso, Yon J. (Department: 2623)
Image analysis
Pattern recognition
Limited to specially coded, human-readable characters
C382S181000
Reexamination Certificate
active
06366696
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to image processing methods and bar code scanners, and more specifically to a visual bar code recognition method.
Bar code symbols provide a fast and accurate means of representing information about an object. Decoding or reading of the bar code is accomplished by translating the patterns of bars and spaces into a unique series of numbers that correspond to a specific item. Currently, the majority of bar codes are read using laser scanners. While these laser systems work well under optimal conditions, they have some inherent disadvantages and limitations. For example, a laser scanner cannot verify that a correct bar code has been scanned by an examination of the item.
Therefore, it would be desirable to provide a visual bar code recognition method, which may be part of a visual bar code scanner.
SUMMARY OF THE INVENTION
In accordance with the teachings of the present invention, a visual bar code recognition method is provided.
The visual bar code recognition method captures a color image of an object containing a bar code. Regardless of the orientation of the bar code within the field-of-view, the system detects the presence of the bar code, and decodes it using the bar/space patterns. It then produces an independent decoding of the human-readable numbers printed on the bar code using OCR. From these two decodings, it determines the identity of the object. It verifies this identity by comparing the physical characteristics of the object from the image with the known features of the product.
The method adds a great deal of decoding flexibility not possible with a laser since a laser scanner can only perform a subset of these tasks.
As long as the bar code is within the focused field of view, the algorithms are capable of locating and decoding the bar code regardless of orientation.
Error detection and correction are provided in two ways: (a) Multiple scan lines are passed through the bar code allowing for partial decoding of several lines and recombining into a final result and (b) Optical Character Recognition (OCR) on the characters below the bar code normally used for manual entry allow for an independent decoding.
After decoding, products may be verified by comparing the known physical characteristics (color, size, shape, texture, etc.) of the decoded product with the features found in the captured image.
The method is applicable to both processing on a single frame static image (such as with a hand-held camera) or on a real-time image stream. The implementations of these ideas are different in each case but the underlying process is identical.
It is accordingly an object of the present invention to provide a visual bar code recognition method.
It is another object of the present invention to provide a visual bar code recognition method which uses a camera to capture an image of an item having a bar code.
It is another object of the present invention to provide a visual bar code recognition method which uses a camera to capture an image of an item having a bar code, and which locates and decodes the bar code.
It is another object of the present invention to provide a visual bar code recognition method which uses a camera to capture an image of an item having a bar code, and which verifies the contents of the bar code using optical character recognition (OCR).
It is another object of the present invention to provide a visual bar code recognition method which uses a camera to capture an image of an item having a bar code, and which verifies the contents of the bar code by comparing features of the item from the image with features in a product database.
It is another object of the present invention to provide a visual bar code recognition method which uses a camera to capture an image of an item having a bar code which may be static or moving.
REFERENCES:
patent: 3744025 (1973-07-01), Bilgutay
patent: 3854035 (1974-12-01), Tyler et al.
patent: 4027142 (1977-05-01), Paup et al.
patent: 4044227 (1977-08-01), Holm et al.
patent: 4147295 (1979-04-01), Nojiri et al.
patent: 4192452 (1980-03-01), Hashimoto et al.
patent: 4408344 (1983-10-01), McWaters et al.
patent: 4473746 (1984-09-01), Edmonds
patent: 4641347 (1987-02-01), Clark et al.
patent: 4680457 (1987-07-01), Robertson
patent: 4748317 (1988-05-01), Satoh
patent: 4806741 (1989-02-01), Robertson
patent: 4902883 (1990-02-01), Poland
patent: 4939355 (1990-07-01), Rando et al.
patent: 4958064 (1990-09-01), Kirkpatrick
patent: 5086215 (1992-02-01), Carsner et al.
patent: 5115888 (1992-05-01), Schneider
patent: 5120940 (1992-06-01), Willsie
patent: 5194722 (1993-03-01), Mergenthaler et al.
patent: 5247154 (1993-09-01), Ahmed
patent: 5276315 (1994-01-01), Surka
patent: 5352878 (1994-10-01), Smith et al.
patent: 5367578 (1994-11-01), Golem et al.
patent: 5463700 (1995-10-01), Nakazawa
patent: 5587575 (1996-12-01), Leitner et al.
Hertz Lois H.
Ming John C.
Su Kevin K.
Couso Yon J.
Martin Paul W.
NCR Corporation
Priest & Goldstein PLLC
LandOfFree
Visual bar code recognition method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Visual bar code recognition method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Visual bar code recognition method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2844877