System and method of locating a non-textual region of an electronic document or image that matches a user-defined description of the region

• US 20030223637A1
• Filed: 05/29/2002
• Published: 12/04/2003
• Est. Priority Date: 05/29/2002
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Simske, Steve John, Auter, David Eugene
• Granted Patent: US 7,050,630 B2
• Time in Patent Office: Days
• US Class Current: 382/176
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/56 having vectorial format
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method of locating a non-textual region of an electronic document or image that matches a user-defined description of the region includes comparing non-textual regions of each of a corpus of electronic documents with the user-defined description and identifying non-textual regions of the electronic documents that match the user-defined description according to pre-determined criteria. A system for locating a non-textual region of an electronic document or image based on a user-defined description of the region includes a user interface for creation of the user-defined description of the region, and a zoning analysis engine for segmenting the electronic document into regions including non-textual regions, comparing the non-textual regions with the user-defined description and identifying non-textual regions which match the user-defined description according to pre-determined criteria.

Claims

1. A method of locating a non-textual region of an electronic document or image that matches a user-defined description of said region, said method comprising:

comparing non-textual regions of each of a corpus of electronic documents with said user-defined description; and

identifying non-textual regions of said electronic documents that match said user-defined description according to pre-determined criteria.

2. The method of claim 1, further comprising generating said user-defined description using scalable vector graphics.

3. The method of claim 1, further comprising generating said user-defined description by scanning a sample of said non-textual region.

4. The method of claim 1, further comprising extracting data from a non-textual region identified as matching said user-defined description.

5. The method of claim 4, further comprising defining a set of algorithms that are performed on said non-textual region identified as matching said user-defined description to extract said data from said non-textual region.

6. The method of claim 1, further comprising contributing documents to said corpus of electronic documents by scanning hardcopy documents.

7. The method of claim 1, further comprising flagging an electronic document containing a non-textual region that matches said user-defined description.

8. The method of claim 1, wherein said non-textual region is a modulation transfer function target, said method further comprising:

using said modulation transfer function target from said electronic documents to assess scan quality of said electronic documents.

9. A system for locating a non-textual region of an electronic document or image based on a user-defined description of said region, said system comprising:

a user interface for creation of said user-defined description of said region; and

a zoning analysis engine for segmenting said electronic document into regions including non-textual regions, comparing said non-textual regions with said user-defined description and identifying non-textual regions which match said user-defined description according to pre-determined criteria.

10. The system of claim 9, further comprising a general-purpose computer, wherein said user interface and said zoning analysis engine are provided by an application running on said general-purpose computer.

11. The system of claim 10;

further comprising a scanner connected to said computer for generating said electronic document from a hardcopy document.

12. The system of claim 9, wherein said user interface comprises a scanner, said user-defined description being generated in accordance with a sample scanned on said scanner.

13. The system of claim 9, wherein said user-defined description describes said region using scalable vectors.

14. Computer-readable instructions stored on a medium for storing computer-readable instructions, said instructions causing a processor to:

segment each of a corpus of electronic documents into textual and non-textual regions;

compare said non-textual regions of each said electronic documents with a user-defined description of a target region; and

identify non-textual regions of said electronic documents that match said user-defined description of said target region according to pre-determined criteria.

15. The computer-readable instructions of claim 14, further comprising a user interface for allowing a user to create said user-defined description of said target region.

16. The computer-readable instructions of claim 15, wherein said user interface displays a graphic representation of a scanned sample of said target region.

17. The computer-readable instructions of claim 14, wherein said computer readable instructions further cause said processor to extract data from a non-textual region identified as matching said user-defined description of said target region.

18. The computer-readable instructions of claim 17, further comprising a set of algorithms that are performed on said non-textual region identified as matching said user-defined description to extract said data from said non-textual region.

20. The system of claim 18, further comprising means for extracting data from a non-textual region identified as matching said user-defined description.

19. A system for locating a non-textual region of an electronic document or image that matches a user-defined description of said region, said system comprising:

means for comparing non-textual regions of each of a corpus of electronic documents with said user-defined description; and

means for identifying non-textual regions of said electronic documents that match said user-defined description according to pre-determined criteria.