Methods and systems for finding elements in optical character recognition documents

Patent metadata

Field	Value
Publication number	US-10970533-B2
Application number	US-201916460625-A
Country	US
Kind code	B2
Filing date	Jul 2, 2019
Priority date	Jul 2, 2019
Publication date	Apr 6, 2021
Grant date	Apr 6, 2021

Abstract

Embodiments for finding elements in optical character recognition (OCR) documents are provided. An indication of a selected portion of document is received. Salient pixels in the selected portion of the document are determined. Properties of the salient pixels in the selected portion of the document are identified. The properties of the salient pixels in the selected portion of the document are compared to properties of pixels in each of a plurality of portions of an OCR-converted version of the document. A cognitive analysis is utilized to select at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document.

First claim

The invention claimed is:

1. A method for finding elements in optical character recognition (OCR) documents comprising:
receiving an indication of a selected portion of document;
determining salient pixels in the selected portion of the document;
identifying properties of the salient pixels in the selected portion of the document;
comparing the properties of the salient pixels in the selected portion of the document to properties of pixels in each of a plurality of portions of an OCR-converted version of the document; and
utilizing a cognitive analysis to select at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document.

2. The method of claim 1 , wherein said selection of the at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document is performed utilizing a similarity metric.

3. The method of claim 1 , wherein the identifying of the properties of the salient pixels in the selected portion of the document includes determining a relationship between the salient pixels in the selected portion of the document to other pixels in the document.

4. The method of claim 3 , wherein the determining of the relationship between the salient pixels in the selected portion of the document to the other pixels in the document is performed utilizing a geometric distance metric.

5. The method of claim 1 , wherein the determining of the salient pixels in the selected portion of the document includes receiving an indication of the salient pixels from a user, is performed utilizing a machine learning method, or a combination thereof.

6. The method of claim 1 , wherein each of the plurality of portions of the OCR-converted version of the document is the same size as the selected portion of the document.

7. The method of claim 1 , further comprising generating an indication of the suspected matches to the selected portion of the document.

8. A system for finding elements in optical character recognition (OCR) documents comprising:
a processor executing instructions stored in a memory device, wherein the processor:
receives an indication of a selected portion of document;
determines salient pixels in the selected portion of the document;
identifies properties of the salient pixels in the selected portion of the document;
compares the properties of the salient pixels in the selected portion of the document to properties of pixels in each of a plurality of portions of an OCR-converted version of the document; and
utilizes a cognitive analysis to select at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document.

9. The system of claim 8 , wherein said selection of the at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document is performed utilizing a similarity metric.

10. The system of claim 8 , wherein the identifying of the properties of the salient pixels in the selected portion of the document includes determining a relationship between the salient pixels in the selected portion of the document to other pixels in the document.

11. The system of claim 10 , wherein the determining of the relationship between the salient pixels in the selected portion of the document to the other pixels in the document is performed utilizing a geometric distance metric.

12. The system of claim 8 , wherein the determining of the salient pixels in the selected portion of the document includes receiving an indication of the salient pixels from a user, is performed utilizing a machine learning method, or a combination thereof.

13. The system of claim 8 , wherein each of the plurality of portions of the OCR-converted version of the document is the same size as the selected portion of the document.

14. The system of claim 8 , wherein the processor further generates an indication of the suspected matches to the selected portion of the document.

15. A computer program product for finding elements in optical character recognition (OCR) documents, by a processor, the computer program product embodied on a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that receives an indication of a selected portion of document;
an executable portion that determines salient pixels in the selected portion of the document;
an executable portion that identifies properties of the salient pixels in the selected portion of the document;
an executable portion that compares the properties of the salient pixels in the selected portion of the document to properties of pixels in each of a plurality of portions of an OCR-converted version of the document; and
an executable portion that utilizes a cognitive analysis to select at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document.

16. The computer program product of claim 15 , wherein said selection of the at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document is performed utilizing a similarity metric.

17. The computer program product of claim 15 , wherein the identifying of the properties of the salient pixels in the selected portion of the document includes determining a relationship between the salient pixels in the selected portion of the document to other pixels in the document.

18. The computer program product of claim 17 , wherein the determining of the relationship between the salient pixels in the selected portion of the document to the other pixels in the document is performed utilizing a geometric distance metric.

19. The computer program product of claim 15 , wherein the determining of the salient pixels in the selected portion of the document includes receiving an indication of the salient pixels from a user, is performed utilizing a machine learning method, or a combination thereof.

20. The computer program product of claim 15 , wherein each of the plurality of portions of the OCR-converted version of the document is the same size as the selected portion of the document.

21. The computer program product of claim 15 , wherein the computer-readable program code portions further include an executable portion that generates an indication of the suspected matches to the selected portion of the document.

Assignees

• IBM

Inventors

• Phipps Christopher
• Katz Edward
• Beller Charles

Classifications

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06V30/414 Primary

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06V30/413

  Classification of content, e.g. text, photographs or tables · CPC title

• G06F18/41

  Interactive pattern learning with a human teacher · CPC title

• G06V30/43

  Editing text-bitmaps, e.g. alignment, spacing; Semantic analysis of bitmaps of text without OCR · CPC title