Method and system for training classification and extraction engine in an imaging solution

• US 8,175,377 B2
• Filed: 06/30/2009
• Issued: 05/08/2012
• Est. Priority Date: 06/30/2009
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Moore, John A., Coene, Matthew
• Primary Examiner(s): Werner, Brian P
• Application Number:
  US12/495,069
• Publication Number:
  US 20100329545A1
• Time in Patent Office: 1,043 Days
• Field of Search: None
• US Class Current: 382/159
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 10/987 with the intervention of an operator

Abstract

A method and system for automatically training a document imaging classification and extraction system that switches between a manual mode and an automatic mode based on constant monitoring. A specialized sub-system monitors and records a user interaction with the classification system during the initial manual mode and, in parallel, develops and tests a user configuration with respect to an automated processing engine. The system is capable of being shifted to the automatic mode if a desired acceptability threshold is attained and the document can then be processed automatically. Furthermore, a user can interact with the classification system if the automatic mode fails. Information concerning exception handling can be entered into a training database for continual refinement of the classification and extraction system.

Claims

1. A method for document imaging classification and extraction, said method comprising:

receiving at least one document to be classified with a document input section;

classifying said at least one document manually;

recording a user interaction with respect to a classification unit for said at least one document in association with an image of said at least one document in a manual mode;

automatically shifting a document to an automatic mode if an acceptable threshold limit is attained, based on a classification and extraction model, in response to receiving said document; and

constantly monitoring said acceptable threshold to switch between said manual mode and said automatic mode.

2. The method of claim 1 further comprising processing said document automatically via an automated processing engine.

3. The method of claim 1 further comprising recording said user interaction in association with said image of said at least one document in a training database in a manual mode.

4. The method of claim 3 further comprising:

developing said classification and extraction model from said user interaction; and

testing said user classification and extraction model with respect to an automated processing engine.

5. The method of claim 3 further comprising:

processing said document if said document is not processed successfully in said automatic mode; and

entering information with respect to said document into said training database for a continual refinement of said classification unit.

6. The method of claim 1 further comprising automatically training said classification unit in order to switch between said manual mode and said automatic mode based on said constant monitoring.

7. The method of claim 1 further comprising configuring said classification unit to switch said document to said manual mode by rebooting said classification unit, if a quality associated with said document changes significantly until said acceptable threshold limit is again attained.

8. The method of claim 1 further comprising automatically displaying a representation indicative of a performance and health of said classification unit.

9. A system for document imaging classification and extraction, said system comprising:

a processor;

a data bus coupled to said processor; and

a computer-usable medium embodying computer code, said computer-usable medium being coupled to said data bus, said computer program code comprising instructions executable by said processor and configured for;

receiving at least one document to be classified with a document input section;

classifying at least one document manually;

recording a user interaction with respect to a classification unit for said at least one document in association with an image of said at least one document in a manual mode;

automatically shifting a document to an automatic mode if an acceptable threshold limit is attained, based on a classification and extraction model, in response to receiving said document; and

constantly monitoring said acceptable threshold to switch between said manual mode and said automatic mode.

10. The system of claim 9 wherein said instructions are further configured for processing said document automatically via an automated processing engine.

11. The system of claim 9 wherein said instructions are further configured for recording said user interaction in association with said image of said at least one document in a training database in a manual mode.

12. The system of claim 11 wherein said instructions are further configured for:

developing said classification and extraction model from said user interaction; and

testing said user classification and extraction model with respect to an automated processing engine.

13. The system of claim 11 wherein said instructions are further configured for:

processing said document if said document is not processed successfully in said automatic mode; and

entering information with respect to said document into said training database for a continual refinement of said classification unit.

14. The system of claim 9 wherein said instructions are further configured for automatically training said classification unit in order to switch between said manual mode and said automatic mode based on said constant monitoring.

15. A non-transitory computer-usable medium for document imaging classification and extraction, said non-transitory computer-usable medium embodying computer program code, said computer program code comprising computer executable instructions configured for:

receiving at least one document to be classified with a document input section;

classifying said at least one document manually;

recording a user interaction with respect to a classification unit for said at least one document in association with an image of said at least one document in a manual mode;

automatically shifting a document to an automatic mode if an acceptable threshold limit is attained, based on a classification and extraction model, in response to receiving said document; and

constantly monitoring said acceptable threshold to switch between said manual mode and said automatic mode.

16. The non-transitory computer-usable medium of claim 15 wherein said embodied computer program code further comprises computer executable instructions configured for processing said document automatically via an automated processing engine.

17. The non-transitory computer-usable medium of claim 15 wherein said embodied computer program code further comprises computer executable instructions configured for recording said user interaction in association with said image of said at least one document in a training database in a manual mode.

18. The non-transitory computer-usable medium of claim 17 wherein said embodied computer program code further comprises computer executable instructions configured for:

developing said classification and extraction model from said user interaction; and

testing said user classification and extraction model with respect to an automated processing engine.

19. The non-transitory computer-usable medium of claim 17 wherein said embodied computer program code further comprises computer executable instructions configured for:

processing said document if said document is not processed successfully in said automatic mode; and

entering information with respect to said document into said training database for a continual refinement of said classification unit.