Automatically extracting graphical bar codes

• US 20020196979A1
• Filed: 06/07/2001
• Published: 12/26/2002
• Est. Priority Date: 06/07/2001
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Yen, Jonathan, Shaked, Doron, Keshet, Renato, Levy, Avraham
• Granted Patent: US 6,895,116 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06K 7/14 using light without selection of wavelength, e.g. sensing reflected white light G06K7/10831 - G06K7/1097 take precedence
• CPC Class Codes: G06K 7/1443 locating of the code in an image

Abstract

Systems and methods for automatically extracting a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode embedded information) are described. In accordance with this automatic extraction scheme, a graphical bar code may be isolated from a composite image in a way that preserves the information-containing graphical modulations encoding the embedded information and avoids corrupting artifacts, such as markings contained in the composite image. The resulting extracted graphical bar code readily may be processed into a format that is tailored to the requirements of a decoding system that may be particularly sensitive to noise, such as extraneous markings and image corruption. In addition, this automatic extraction scheme robustly handles missed and incorrect detections.

Claims

1. A method of extracting from an input image a graphical bar code containing graphically encoded information, comprising:

trimming non-graphical bar code regions from the input image based upon estimated position coordinates for a detected graphical bar code candidate to produce a trimmed graphical bar code candidate for decoding.

2. The method of claim 1, further comprising cropping the input image before trimming based upon estimated position coordinates for a detected graphical bar code candidate to produce an inclusive image region encompassing the detected graphical bar code.

3. The method of claim 1, further comprising computing the angular orientation of the detected graphical bar code candidate.

4. The method of claim 3, wherein the non-graphical bar code regions are trimmed based upon intensity histogram profiles obtained by summing intensity values along orthogonal axes corresponding to the computed angular orientation of the detected graphical bar code candidate.

5. The method of claim 4, wherein the non-graphical bar code regions are trimmed based upon application of a threshold to the intensity histogram profiles.

6. The method of claim 4, wherein the non-graphical bar code regions are trimmed based upon a comparison of expected graphical bar code dimensions with the intensity histogram profiles.

7. The method of claim 3, further comprising de-skewing the detected graphical bar code candidate before the non-graphical bar code regions are trimmed.

8. The method of claim 1, further comprising rotating the input image and processing the rotated input image to detect a graphical bar code candidate in response to a failure to detect a graphical bar code candidate in the input image before rotation.

9. The method of claim 1, further comprising detecting a graphical bar code candidate based upon a second training sample in response to a failure to detect a graphical bar code candidate in the input image based upon a first training sample.

10. The method of claim 9, wherein the second training sample is a rotated version of the first training sample.

11. The method of claim 1, further comprising extracting a second graphical bar code candidate detected in the input image in response to a determination that a first extracted graphical bar code candidate does not correspond to the graphical bar code.

12. The method of claim 1, further comprising resolution scaling the trimmed graphical bar code candidate.

14. The system of claim 13, wherein the graphical bar code extractor is configured to crop the input image before trimming based upon estimated position coordinates for a detected graphical bar code candidate to produce an inclusive image region encompassing the detected graphical bar code.

15. The system of claim 13, wherein the non-graphical bar code regions are trimmed based upon intensity histogram profiles obtained by summing intensity values along orthogonal axes corresponding to a computed angular orientation of the detected graphical bar code candidate.

16. The system of claim 13, wherein the graphical bar code extractor is configured to de-skew the detected graphical bar code candidate before the non-graphical bar code regions are trimmed.

17. The system of claim 13, wherein the graphical bar code extractor is configured to rotate the input image and process the rotated input image to detect a graphical bar code candidate in response to a failure to detect a graphical bar code candidate in the input image before rotation.

18. The system of claim 13, wherein the graphical bar code extractor is configured to detect a graphical bar code candidate based upon a second training sample in response to a failure to detect a graphical bar code candidate in the input image based upon a first training sample.

19. The system of claim 13, wherein the graphical bar code extractor is configured to extract a second graphical bar code candidate detected in the input image in response to a determination that a first extracted graphical bar code candidate does not correspond to the graphical bar code.

13. A system for extracting from an input image a graphical bar code containing graphically encoded information, comprising a graphical bar code extractor configured to:

trim non-graphical bar code regions from the input image based upon estimated position coordinates for a detected graphical bar code candidate to produce a trimmed graphical bar code candidate for decoding.

20. A computer program residing on a computer-readable medium and comprising computer-readable instructions for causing a computer to:

trim non-graphical bar code regions from the input image based upon estimated position coordinates for a detected graphical bar code candidate to produce a trimmed graphical bar code candidate for decoding.