Method for automatic conversion of paper records to digital form

• US 9,531,906 B2
• Filed: 06/11/2010
• Issued: 12/27/2016
• Est. Priority Date: 06/11/2010
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Martin, Nathaniel G., Austin, Paul R.
• Primary Examiner(s): Nguyen, Madelein
• Application Number:
  US12/813,584
• Publication Number:
  US 20110304890A1
• Time in Patent Office: 2,391 Days
• Field of Search: 358/540, 358/538, 358/537, 358/530, 358/450, 358/452, 358/462, 358/464, 358/470, 358/1.9, 358/1.16, 358/1.18, 358/1.1
• US Class Current: 1/1
• CPC Class Codes: H04N 1/00331 with an apparatus performing optical character recognition character recognition G06V30/10
• CPC Class Codes: H04N 1/32112 in a separate computer file, document page or paper sheet, e.g. a fax cover sheet H04N1/32122 takes precedence
• CPC Class Codes: H04N 1/32149 Methods relating to embedding, encoding, decoding, detection or retrieval operations
• CPC Class Codes: H04N 1/32309 in colour image data
• CPC Class Codes: H04N 1/32325 the embedded data being visible
• CPC Class Codes: H04N 2201/3226 of identification information or the like, e.g. ID code, index, title, part of an image, reduced-size image
• CPC Class Codes: H04N 2201/3257 relating to the original, the input device or the input process, e.g. scanner profile

Abstract

A method of scanning a set of documents in a container such as a file folder or storage box where the container contains a unique label containing identification associated with the documents in the container. The label comprises both alphanumeric characters and color information where each character is associated with a particular color. By scanning the container and analyzing the image of the container the unique identification can be retrieved with increased reliability by using both the color and alphanumeric information.

Claims

1. A method for extracting identification information from a container to facilitate the storing and indexing of electronic images produced from scanning documents contained in the container, comprising:

scanning, using a scanner, a portion of the container to generate electronic data representing an electronic image of the scanned portion of the container, the electronic data including color space image data representing an individual color and alphanumeric data representing an individual alphanumeric character;

electronically analyzing the color space image data within a predetermined area of the electronic image to identify the individual color within the analyzed predetermined area of the electronic image;

electronically analyzing the alphanumeric data within a predetermined area of the electronic image to identify the alphanumeric individual character within the analyzed predetermined area of the electronic image;

electronically identifying, based upon both the identified color and the identified alphanumeric character, index information for the container;

scanning, using a scanner, the documents within the container to generate image data;

electronically labeling the image data in accordance with the identified index information for the container; and

storing, in a data storage device, the image data at a location within the data storage device, associated with the identified index information for the container.

2. The method as claimed in claim 1, further comprising:

providing a template that defines the predetermined area of the electronic image that contains the color space image data and the alphanumeric data to be analyzed.

3. The method as claimed in claim 1, wherein each alphanumeric character on the container is surrounded by a specific color such that the identity of the alphanumeric character can be electronically verified by electronically comparing the identity of the alphanumeric character with the identity of the surrounding color.

4. The method as claimed in claim 1, wherein each alphanumeric character on the container is printed by a specific color such that the identity of the alphanumeric character can be electronically verified by electronically comparing the identity of the alphanumeric character with the identity of the color used to print the character.

5. The method as claimed in claim 1, further comprising:

electronically inserting the identified index information for the container into metadata of the image data.

6. The method as claimed in claim 1, further comprising:

electronically processing image data in accordance with the identified index information for the container.

7. The method as claimed in claim 1, further comprising:

accepting input from a user interface that defines the location of the label containing the color space image data and the alphanumeric data.

8. The method as claimed in claim 1, wherein the color space image data is RGB image data.

9. The method as claimed in claim 8, wherein the identification of the individual color within the analyzed predetermined area of the electronic image is realized by matching the RGB values of the color space image data against a set of RGB values that are associated with a predefined color set.

10. The method as claimed in claim 1, wherein optical character recognition is used to analyze the alphanumeric data to identify the alphanumeric individual characters within the analyzed predetermined area of the electronic image.

11. A system for extracting identification information from a container, the container containing a plurality of documents comprising:

a scanner, the scanner generating color digital image data of objects placed on its input platen; and

a processor, operatively connected to said scanner, to receive the color digital image data and to convert the color digital image data into color space image data representing an individual color and alphanumeric data representing an individual alphanumeric character;

said processor extracting, from the color digital image data, a portion of the color digital image data that contains a label;

said processor analyzing the color space image data of the portion of the color digital image data that contains the label to identify a color of the portion of the color digital image data that contains the label;

said processor converting the identified color into an equivalent alphanumeric form;

said processor analyzing, the alphanumeric data of the portion of the color digital image data that contains the label to identify the alphanumeric character in the portion of the color digital image data that contains the label;

said processor comparing the equivalent alphanumeric form of the converted identified color to the identified alphanumeric character in the portion of the color digital image data that contains the label to verify that the equivalent alphanumeric form of the converted identified color and the identified alphanumeric character are the same;

said processor, when the equivalent alphanumeric form of the converted identified color and the identified alphanumeric character are verified as the same, identifying, based upon the equivalent alphanumeric form of the converted identified color and the identified alphanumeric character, index information for the container when the equivalent alphanumeric form of the converted identified color and the identified alphanumeric character are the same;

said processor labeling the image data in accordance with the identified index information for the container;

said processor causing the labeled image data to be stored in a data storage device at a location associated with the identified index information for the container.

12. The system as claimed in claim 11, further comprising:

a user interface to enable a user to provide a template that defines the predetermined area of the color digital image that contains the color space image data and alphanumeric data to be analyzed.

13. The system as claimed in claim 11, wherein each alphanumeric character on the container is surrounded by a specific color such that the identity of the alphanumeric character can be verified by said processor comparing the identity of the alphanumeric character with the identity of the surrounding color.

14. The system as claimed in claim 11, wherein each alphanumeric character on the container is printed by a specific color such that the identity of the alphanumeric character can be verified by said processor comparing the identity of the alphanumeric character with the identity of the color used to print the alphanumeric character.

15. The system as claimed in claim 11, wherein said processor electronically inserts the identified index information for the container into metadata of the image data.

16. The system as claimed in claim 11, wherein said processor electronically processes image data in accordance with the identified index information for the container.

17. The system as claimed in claim 11, wherein the color space image data is RGB image data.

18. The system as claimed in claim 17, wherein the identification of the color of the portion of the color digital image data that contains the label is realized by matching the RGB values of the color space image data against a set of RGB values that are associated with a predefined color set.

19. The system as claimed in claim 11, wherein optical character recognition is used to analyze the alphanumeric data to identify the alphanumeric individual characters within the analyzed predetermined area of the electronic image.