AUTOMATED REDACTION

• US 20150071542A1
• Filed: 09/06/2013
• Published: 03/12/2015
• Est. Priority Date: 09/06/2013
• Status: Active Grant

• Current Assignee: Lighthouse Document Technologies, Inc. (Lighthouse Technologies Holdings Corp.)
• Original Assignee: Lighthouse Document Technologies, Inc. (Lighthouse Technologies Holdings Corp.)
• Inventors: Belger, Geoffrey Alan David, Dahl, Christopher Byron, Motyka Jones, Debora Noemi, O'Neill, Kevin Patrick, Mazelis, Vladas Walter, Byington, Nathaniel, Holt, Beau Hodges, Olson, John Charles
• Granted Patent: US 9,436,882 B2
• Time in Patent Office: Days
• US Class Current: 382/177
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/226 of cursive writing
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/43 Editing text-bitmaps, e.g. alignment, spacing; Semantic analysis of bitmaps of text without OCR

Abstract

In embodiments, one or more computer-readable media may have instructions stored thereon which, when executed by a processor of a computing device provide the computing device with a redaction module. The redaction module may be configured to receive a request to redact a selection of text from a document and identify instances of the text occurring within the document through an analysis of word coordinate information of an image of the document. The redaction module may further be configured to generate redaction information, including redaction coordinates, the redaction coordinates may be based on the word coordinate information associated with respective instances of the text occurring within the document. The redactions, when applied to the image in accordance with the redaction coordinates, may redact the respective instances of the text. Other embodiments may be described and/or claimed.

Claims

1. One or more computer-readable media having instructions stored thereon which, when executed by a processor of a computing device provide the computing device with a redaction module configured to:

receive a request to redact a selection of text from a document;

identify instances of the text occurring within the document through an analysis of word coordinate information of an image of the document; and

generate redaction information, including redaction coordinates, the redaction coordinates based on the word coordinate information associated with respective instances of the text occurring within the document, wherein redactions applied to the image, in accordance with the redaction coordinates, redact the respective instances of the text.

2. The one or more computer-readable media of claim 1, wherein the selection of text comprises one or more words, phrases, sentences, or paragraphs.

3. The one or more computer-readable media of claim 1, wherein redactions applied to the image in accordance with the redaction coordinates redact whitespace and punctuation occurring within the respective instances of the text.

4. The one or more computer-readable media of claim 1, wherein the redaction module is further configured to identify groups of words within the document as instances of the text in the document by computation of respective Levenshtein distance values between the groups of words and the text, and a determination of whether each Levenshtein distance value is within a determined threshold.

5. The one or more computer-readable media of claim 4, wherein the determined threshold is based upon the number of characters contained within the text.

6. The one or more computer-readable media of claim 4, wherein computation and determination further comprises reduction of the Levenshtein distance value between a group of words and the text, on detection that the Levenshtein distance value between the group of words and the text is within a first threshold, wherein reduction of the Levenshtein distance between a group of words and the text is based on a correlation of characters that contribute to the Levenshtein distance value with one or more characters commonly misinterpreted by the OCR process;

and

wherein determination further comprises identification of the group of words as an instance of the text when the reduced Levenshtein distance value is within a second threshold.

7. The one or more computer-readable media of claim 6, wherein the first and second thresholds are based on the number of characters contained within the text.

8. The one or more computer-readable media of claim 1, wherein to receive further comprises receipt of the selected text and the document.

9. The one or more computer-readable media of claim 8, wherein the redaction module is further configured to generate an image of the document to be redacted when the request includes copies of the document to be redacted.

10. The one or more computer-readable media of claim 1, wherein the word coordinate information is generated by an optical character recognition (OCR) process performed on the image of the document.

11. A system for redacting documents, comprising:

a processor; and

a redaction module configured to cause the processor to;

receive a request to redact a selection of text from a document;

identify instances of the text occurring within the document through an analysis of word coordinate information of an image of the document; and

generate redaction information, including redaction coordinates, the redaction coordinates based on the word coordinate information associated with respective instances of the text occurring within the document, wherein redactions applied to the image, in accordance with the redaction coordinates, redact the respective instances of the text.

12. The system of claim 11, wherein the selection of text comprises one or more words, phrases, sentences, or paragraphs.

13. The system of claim 11, wherein redactions applied to the image in accordance with the redaction coordinates redact whitespace and punctuation occurring within the respective instances of the text.

14. The system of claim 11, wherein the redaction module is further configured to identify groups of words within the document as instances of the text in the document by computation of respective Levenshtein distance values between the groups of words and the text, and a determination of whether each Levenshtein distance value is within a determined threshold.

15. The system of claim 14, wherein the determined threshold is based upon the number of characters contained within the text.

16. The system of claim 14, wherein computation and determination further comprises reduction of the Levenshtein distance value between a group of words and the text, on detection that the Levenshtein distance value between the group of words and the text is within a first threshold, wherein reduction of the Levenshtein distance between a group of words and the text is based on a correlation of characters that contribute to the Levenshtein distance value with one or more characters commonly misinterpreted by the OCR process;

and

wherein determination further comprises identification of the group of words as an instance of the text when the reduced Levenshtein distance value is within a second threshold.

17. The system of claim 16, wherein the first and second thresholds are based on the number of characters contained within the text.

18. The system of claim 11, wherein to receive further comprises receipt of the selected text and the document.

19. The system of claim 18, wherein the redaction module is further configured to generate an image of the document to be redacted when the request includes copies of the document to be redacted.

20. The system of claim 11, wherein the word coordinate information generated by an optical character recognition (OCR) process performed on the image.

21. A computer-implemented method for redacting documents, comprising:

receiving, by a redaction module of a computing device, a request to redact a selection of text from a document;

identifying, by the redaction module, instances of the text occurring within the document through an analysis of word coordinate information of an image of the document;

generating, by the redaction module, redaction information, including redaction coordinates, the redaction coordinates based on the word coordinate information associated with respective instances of the text occurring within the document, wherein redactions applied to the image, in accordance with the redaction coordinates, redact the respective instances of the text.

22. The computer-implemented method of claim 21, wherein the selection of text comprises one or more words, phrases, sentences, or paragraphs.

23. The computer-implemented method of claim 21, wherein redactions applied to the image in accordance with the redaction coordinates redact whitespace and punctuation occurring within the respective instances of the text.

24. The computer-implemented method of claim 21, further comprising identifying groups of words within the document as instances of the text in the document, by the redaction module, by computing respective Levenshtein distance values between the groups of words and the text, and determining whether each Levenshtein distance value is within a determined threshold.

25. The computer-implemented method of claim 24, wherein the determined threshold is based upon the number of characters contained within the text.

26. The computer-implemented method of claim 24, wherein computing and determining further comprises

reducing the Levenshtein distance value between a group of words and the text, on detecting the Levenshtein distance value between the group of words and the text is within a first threshold wherein reducing the Levenshtein distance between a group of words and the text is based on a correlation of characters contributing to the Levenshtein distance value with one or more characters commonly misinterpreted by the OCR process;

and

wherein determining further comprises identifying the group of words as an instance of the text when the reduced Levenshtein distance value is within a second threshold.

27. The computer-implemented method of claim 26, wherein the first and second thresholds are based on the number of characters contained within the text.

28. The computer-implemented method of claim 21, wherein receiving comprises receive the selected text and the document.

29. The computer-implemented method of claim 28, further comprising generating an image of the document to be redacted when the request includes copies of the document to be redacted.

30. The computer implemented method of claim 21, wherein the word coordinate information generated by an optical character recognition (OCR) process performed on the image.

31. The computer implemented method of claim 21, further comprising:

identifying, by the redaction module, one or more additional documents to redact the selection of text from by searching a repository of documents for one or more additional documents containing the selection of text or similar text;

identifying, by the redaction module, instances of the text occurring within the one or more additional documents through an analysis of word coordinate information of one or more images of the one or more additional documents;

generating, by the redaction module, redaction information, including second redaction coordinates, the second redaction coordinates based on the word coordinate information associated with respective instances of the text occurring within the one or more additional documents, wherein redactions applied to the image, in accordance with the second redaction coordinates, redact the respective instances of the text in the one or more additional documents.

32. The computer implemented method of claim 21, further comprising:

receiving, by the redaction module, a request to copy a generated redaction from one page to another page of a document or from one document to another document; and

copying the redaction coordinates of the generated redaction to the another page or the another document, wherein redactions applied to the another page or another document, in accordance with the redaction coordinates of the generated redaction copied to another page or another document, redact content located within the redaction coordinates on the another page or another document.