Method and apparatus for reading and decoding information

• US 6,778,683 B1
• Filed: 12/08/1999
• Issued: 08/17/2004
• Est. Priority Date: 12/08/1999
• Status: Expired due to Term

• Current Assignee: Federal Express Corporation (FedEx Corporation)
• Original Assignee: Federal Express Corporation (FedEx Corporation)
• Inventors: Skaaksrud, Ole-Petter, Bonner, Brett Bracewell, Jankevics, Andris
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US09/456,433
• Time in Patent Office: 1,714 Days
• Field of Search: 382/100, 382/101, 382/102, 382/181, 382/317, 235/462.01, 235/462.07, 235/470, 715/505, 715/507, 209/504, 209/584, 209/900
• US Class Current: 382/101
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: G06V 30/274 Syntactic or semantic context, e.g. balancing
• CPC Class Codes: Y10S 209/90 Sorting flat-type mail

Abstract

A method and apparatus is disclosed for reading and decoding information extracted from a form. In the system of the present invention, packages are randomly placed on a conveyor belt, with their labels facing a two-camera subassembly. As the conveyor belt moves, the two-camera subassembly continuously takes images of the belt underneath the overhead camera. The design of the camera permits it to take a high resolution image of a non-singulated, unjustified package flow. A digital image of the packages within the field of view of the camera is then transferred to the processing system for analysis. The processing system identifies individual packages in the image, extracts them and then analyzes the information written on the package labels. The analysis process utilizes conventional Optical Character Recognition (OCR) and Intelligent Character Recognition (ICR) techniques to evaluate the information written on the package label. Once the information is decoded, the system either accesses a database record associated with the decoded machine-readable code, or creates a new record. When an unknown word image is encountered, the field-specific recognition process is aided by use of lexicon information, optimized based on installation-specific or user-specific criteria. The lexicon information is continuously revised based on processed form information. In a preferred embodiment, verified destination addresses associated with a user are alphabetized or rank-ordered based on frequency of occurrence. It is only after the system determines that the originating user is not stored in the database does it resort to the ZIP+4 or similar database to verify a destination address.

Claims

1. A method of capturing and processing information from a plurality of forms concurrently the method comprising the steps of:

capturing an image of a plurality of forms randomly positioned on a moving conveyor belt and visible to an imager, each one of said forms being respectively associated with one of a plurality of packages;

locating at least one of said plurality of forms in said captured image, said at least one form comprising a plurality of information data fields; and

decoding at least one of said plurality of information data fields.

2. The method of claim 1 including the step of repeating the locating and decoding steps until every form in said captured image has been processed.

3. The method of claim 1 wherein said image is comprised of a plurality of non-singulated forms.

4. The method of claim 3 wherein said captured image is comprised of a plurality of unjustified forms.

5. The method of claim 1 wherein said locating step is further comprised of the steps of:

locating a predetermined pattern in said captured image;

locating at least one fiduciary mark in said captured image, said at least one fiduciary mark does not exceed a predetermined distance from said predetermined pattern; and

determining a region of interest, said region of interest circumscribes an area including said predetermined pattern and said at least one fiduciary mark.

6. The method of claim 5, wherein said predetermined pattern is a machine readable code.

7. The method of claim 5, wherein said predetermined pattern is numeric, alphanumeric, or alphabetic text.

8. The method of claim 5, wherein said predetermined pattern is a picture.

9. The method of claim 5 wherein said step of locating a predetermined pattern is further comprised of the steps of:

determining that a portion of said predetermined pattern is missing from said captured image; and

combining said captured image with at least one prestored image to create a complete determined pattern.

10. The method of claim 5 wherein said determining step is further comprised of the steps of:

determining that a portion of the region of interest is missing from said captured image; and

combining said captured image with at leas tone prestored image to create a complete region of interest.

11. The method of claim 1 wherein said decoding step is comprised of the steps of:

measuring a spatial relationship between at least one fiduciary mark and a predetermined pattern, said spatial relationship identifying a location and format of at least one of said plurality of information data fields located on said form; and

decoding at least one of said plurality of information data fields.

12. The method of claim 11 wherein the decoding step is comprised of the following steps:

identifying an originating source associated with said form;

extracting information from at least one of said information data fields;

decoding said extracted information using a recognition engine, wherein said recognition engine is determined by the location and format of said information data field;

comparing said decoded information with a database entry of package information associated with said originating source; and

replacing said decoded information with said package information, provided a predetermined criteria is met.

13. The system of claim 12 further comprising of the step of re-ordering said package information database, provided a predetermined criteria is met.

14. A computer system for capturing and processing information from a plurality of forms traveling on a conveyor belt, concurrently, comprising:

a memory having program instructions; and

a processor configured to use the program instructions to capture an image of said plurality of forms, each one of said forms being associated with one of a plurality of packages respectively, to locate at least one of said plurality of forms in said captured image, wherein said at least one form comprises a plurality of information data fields, and to decode the information on said at least one of said plurality of forms.

15. The computer system according to claim 14, wherein the processor is further configured to repeat the locating and decoding instructions until every form in said captured image has been processed.

16. The computer system according to claim 14 wherein the locating instruction is further comprised of the following instructions:

locate a predetermined pattern in said captured image;

locate at least one fiduciary mark in said captured image, wherein said at least one fiduciary mark does not exceed a predetermined distance from said predetermined pattern; and

determine a region of interest, wherein said region of interest circumscribes an area including said predetermined pattern and said at least one fiduciary mark.

17. The computer system according to claim 16, wherein the determining instruction is further comprised of the following instructions:

determine that a portion of the region of interest is missing from said captured image; and

combine the captured image with at least one prestored image to create a complete region of interest.

18. The computer system according to claim 14, wherein the locating and predetermined pattern instruction is further comprised of the following instructions:

determine that a portion of said predetermined pattern is missing from said captured image; and

combine the captured image with at least one prestored image to create a complete predetermined pattern.

19. The computer system according to claim 14, wherein the decoding instruction is further comprised of the following instructions:

measure a spatial relationship between at least one fiduciary mark and a predetermined pattern, said spatial relationship identifying a location and format of at leas tone of said plurality of information data fields located on said form; and

decode at least one of said plurality of information data fields.

20. The computer system according to claim 19, wherein the decoding instruction is further comprised of the following instructions:

identifying a originating source associated with said form;

extract information from at least one of said information data fields;

decode said extracted information using a recognition engine, wherein said recognition engine is determined by the location and format of said information data field;

compare said decoded information with a database entry of package information associated with said originating source; and

replace said decoded information with said package information, provided a predetermined criteria is met.

21. The system of claim 20 further comprising of the instruction to reorder said data entry of package information, provided a predetermined criteria is met.

22. A system for capturing and processing information from a plurality of forms concurrently, said forms being randomly positioned on a moving conveyor belt and visible, said system comprising:

means for capturing an image of said plurality of forms, each one of said forms being respectively associated with each of a plurality of packages;

means for locating at least one of said plurality of forms in said captured image, wherein said at least one form is comprised of a plurality of information data fields; and

means for decoding the information on said at least one of said plurality of forms.

23. The system of claim 22 including means for executing the means for locating and the means for decoding until every form in said captured image has been processed.

24. The system of claim 22, wherein the means for locating is further comprised of:

means for locating a predetermined pattern in said captured image;

means for locating at least one fiduciary mark in said captured image, said at least one fiduciary mark does not exceed a predetermined distance from said predetermined pattern; and

means for determining a region of interest, said region of interest circumscribes an area including said predetermined pattern and said at least one fiduciary mark.

25. The system of claim 24, wherein the means for locating is further comprised of:

means for determining that a portion of said predetermined pattern is missing from said captured image; and

means for combining said captured image with at least one prestored image to create a complete predetermined pattern.

26. The system of claim 24, wherein the means for determining is further comprised of:

means for determining that a portion of the region of interest is missing from said captured image; and

means for combining said captured image with at least one prestored image to create a complete region of interest.

27. The system of claim 22 wherein the means for decoding is further comprised of:

means for measuring a spatial relationship between at least one fiduciary mark and a predetermined pattern, said spatial relationship identifying a location and format of at least one of said plurality of information data fields located on said form; and

means for decoding at least one of said plurality of information data fields.

28. The system of claim 27 wherein the means for decoding is further comprised of:

means for identifying an originating source associated with said form;

means for extracting information from at least one of said information data fields;

means for decoding said extracted information using a recognition engine, wherein said recognition engine is determined by the location and format of said information data field;

means for comparing said decoded information with a database entry of package information associated with said originating source; and

means for replacing said decoded information with said package information, provided a predetermined criteria is met.

29. The system of claim 28 further comprising of means for re-ordering said package information database, provided a predetermined criteria is met.

30. A method of capturing and processing information from a plurality of forms concurrently, said forms being visible to an imager and associated with a plurality of packages that are randomly positioned on a moving conveyor belt, the method comprising:

capturing an image of said plurality of packages and the associated forms;

locating at least one of said plurality of forms in said captured image, said at least one form comprised of a plurality of information data fields; and

decoding at least one of said plurality of information data fields.

31. The method of claim 30 further including:

repeating the locating and decoding steps until every form in said captured image has been processed.

32. A method of capturing and processing information from a plurality of forms associated with packages concurrently, the method comprising:

capturing an image of a plurality of packages that are randomly positioned on a moving conveyor belt;

locating in said captured image at least one form corresponding to one of the plurality of packages, the at least one form comprised of a plurality of information data fields; and

decoding at least one of said plurality of information data fields.