Method and system for image processing

• US 20040120547A1
• Filed: 07/01/2003
• Published: 06/24/2004
• Est. Priority Date: 12/24/2002
• Status: Active Grant

• Current Assignee: Korber Supply Chain LLC (Siemens AG)
• Original Assignee: Siemens Energy & Automation Incorporated (Siemens AG)
• Inventors: Mampe, John J., Kiani, Shahrom
• Granted Patent: US 7,145,093 B2
• Time in Patent Office: Days
• US Class Current: 382/101
• CPC Class Codes: B07C 3/12 using electric or electronic detecting means B07C3/14 takes precedence
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches
• CPC Class Codes: Y10S 209/939 Video scanning

Abstract

The invention provides a method of processing an image containing written information include the steps of (a) scanning a surface of an object to obtain an image of the surface represented by first image data, (b) creating second image data from the first image data, the second image data having a lower data density than the first image data, (c) analyzing the second image data with first image analysis logic to decode the written information, and (d) if the written information cannot be decoded to a desired extent from the second image data, analyzing the first image data with second image analysis logic different from the first image analysis logic to decode the written information. Steps (a) and (b) preferably use a single scanning device to create the high data density image (e.g., color or grayscale) from which the lower data density image (e.g., binary or black and white) can then be created. The resulting two-stage image analysis provides a significant improvement in OCR results. Further, when a pre-printed bar code is present but does not result in a destination bar code, using the methods of step 7, determining the destination address zip code using OCR techniques, printing the resultant ZIP Code and sorting the mail based on the new OCR derived data.

Claims

1. A method of processing an image containing written information, comprising the steps of:

(a) scanning a surface of an object to obtain an image of the surface represented by first image data;

(b) creating second image data of the image of the surface, the second image data having a lower data density than the first image data;

(c) analyzing the second image data with first image analysis logic to decode the written information; and

(d) if the written information cannot be decoded to a desired extent from the second image data, analyzing the first image data with second image analysis logic different from the first image analysis logic to decode the written information.

2. The method of claim 1, further comprising:

transporting a series of the objects on a conveyor system leading past a scanner which carries out step (a);

repeating steps (a)-(d) for a succession of images generated by each object as it passes the scanner;

maintaining a buffer containing the first image data for a number of consecutive images so that the first image data is maintained in the buffer during step (c); and

accessing the buffer to obtain the image for processing in step (d).

3. The method of claim 2, further comprising sorting the object according to the decoded written information.

4. The method of claim 2, further comprising, following successful analysis of the written information in step (c) for an image, erasing the first image data for that image from the buffer.

5. The method of claim 4, further comprising transferring the first image data to an archival storage medium prior to erasing the image from the buffer.

6. The method of claim 1, wherein the first image data is in a grayscale format and the second image data is in a binary format, and the second image data is derived from the first image data by a computer-implemented image conversion process.

7. The method of claim 3, wherein the objects are mail pieces.

8. The method of claim 7, wherein the images are images of a mail piece surface, step (a) further comprises feeding a series of mail pieces through a scanning device to obtain the succession of images, and the first and second image data are analyzed to obtain destination information.

9. The method of claim 1, wherein the objects are change of address forms, and the written indicia include a name, a new address and a former address.

10. A method of sorting mail pieces on an automated sorting machine, comprising the steps of:

(a) transporting a series of mail pieces on a conveyor system past a scanner, which conveyor then transports the mail pieces to a sorting section of the sorting machine;

(b) scanning a surface of each mail piece with the scanner to obtain an image of the surface represented by first image data;

(c) creating second image data from the first image data, the second image data having a lower data density than the first image data;

(d) analyzing the second image data with first image analysis logic to decode the written information to obtain destination information sufficient for sorting;

(e) if the written information cannot be decoded to a desired extent from the second image data, analyzing the first image data with second image analysis logic different from the first image analysis logic to decode the written information to obtain destination information sufficient for sorting; and

(f) then sorting each mail piece at the sorting section according to the decoded destination information.

11. The method of claim 10, further comprising:

maintaining a buffer containing the first image data for a number of consecutive images so that the first image data is maintained in the buffer during step (d); and

accessing the buffer to obtain the first image data for processing in step (e).

12. The method of claim 10, further comprising:

determining if a mail piece has a postal bar code thereon;

if the mail piece has a postal bar code thereon, analyzing the second image data to decode the postal bar code;

if the decoded postal bar code identifies a destination, ending the method as to such mail piece; and

if the mail piece has a postal bar code thereon that cannot be decoded, analyzing the second image data to decode the postal bar code.

13. The method of claim 12, wherein the bar code is a ZIP plus 4 delivery point bar code.

14. The method of claim 12, wherein if a destination cannot be determined in step (e) until after the mail piece has entered the sorting section, then printing the mail piece with an identification code;

saving the result determined in step (e) to a decision storage unit; and

feeding the mail piece into an output subsystem, which obtains the result from the decision storage unit, reads the identification code, and marks the mail piece with a postal bar code indicating the destination.

15. The method of claim 10, further comprising:

determining if a mail piece has a written address thereon;

if the mail piece has a written address thereon, analyzing the second image data to decode the written address;

if the decoded written address identifies a destination, ending the method as to such mail piece; and

if the mail piece has a written address thereon that cannot be decoded, analyzing the second image data to decode the written address, wherein the first and second image analysis logic each comprise optical character recognition logic.

16. The method of claim 15, further comprising marking a mail piece successfully analyzed in steps (d) or (e) with a postal bar code indicating the destination prior to sorting the mail piece in step (f).

17. The method of claim 15, wherein if a destination cannot be determined in step (e) until after the mail piece has entered the sorting section, then:

printing the mail piece with an identification code;

saving the result determined in step (e) to a decision storage unit; and

feeding the mail piece into an output subsystem, which obtains the result from the decision storage unit, reads the identification code, and marks the mail piece with a postal bar code indicating the destination.

18. A system for processing an image containing written information, comprising:

a scanner configured for scanning a surface of an object to obtain an image of the surface represented by first image data;

means for creating second image data from the first image data, the second image data having a lower data density than the first image data;

means for analyzing the second image data with first image analysis logic to decode the written information; and

means for analyzing the first image data with second image analysis logic different from the first image analysis logic to decode the written information if the written information cannot be decoded to a desired extent from the second image data.