Method and System for Accurately Detecting, Extracting and Representing Redacted Text Blocks in a Document

• US 20200097713A1
• Filed: 09/24/2018
• Published: 03/26/2020
• Est. Priority Date: 09/24/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cramer, Keith D., Resse, Christophe
• Granted Patent: US 10,733,434 B2
• Time in Patent Office: Days
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors

Abstract

A computer-implemented method, system and a computer program product are provided for automatically detecting redaction blocks in an image file document by analyzing the document to identify any redaction block areas and then detecting location information for each redaction block area identified in the document which may be mapped to any associated text fragments in the document based on the location information for each redaction block area and text fragment in the document.

Claims

1. A computer-implemented method for automatically detecting redaction blocks in a document comprising:

receiving, by an information handling system comprising a processor and a memory, the document as an image file;

analyzing, by the information handling system, the document to identify any redaction block areas in the document; and

detecting, by the information handling system, location information for each redaction block area identified in the document.

2. The method of claim 1, further comprising classifying, by the information handling system, each identified redaction block area as a type Ti selected from a group consisting of a text block, a table cell, a checkbox, and unknown.

3. The method of claim 2, where the type Ti is the checkbox which classifies a redaction block area located over a group of labels in the document.

4. The method of claim 1, where each redaction block area is a blacked-out area in the document.

5. The method of claim 1, where detecting location information comprises computing, by the information handling system, a geometric shape and x, y coordinates for each redaction block area.

6. The method of claim 1, further comprising:

applying, by the information handling system, optical character recognition to the document to detect text fragments in the document;

detecting, by the information handling system, location information for each text fragment identified in the document; and

mapping, by the information handling system, each redaction block area to any associated text fragments in the document based on the location information for each redaction block area and text fragment in the document.

7. The method of claim 1, further comprising inserting, by the information handling system, a sentinel string of predetermined characters into the document for each detected redaction block area.

8. The method of claim 1, where analyzing the document comprises applying a redaction block detection process to scan each line of the image file to identify any redacted text blocks by locating a threshold number T1 of consecutive black pixels that are aligned in a threshold number T1 of consecutive rows.

9. An information handling system comprising:

one or more processors;

a memory coupled to at least one of the processors;

a set of instructions stored in the memory and executed by at least one of the processors to automatically detect redaction blocks in a document, wherein the set of instructions are executable to perform actions of;

receiving, by the system, the document as an image file;

analyzing, by the system, the document to identify any redaction block areas in the document; and

detecting, by the system, location information for each redaction block area identified in the document.

10. The information handling system of claim 9, where the set of instructions are executable to classify, by the system, each identified redaction block area as a type Ti selected from a group consisting of a text block, a table cell, a checkbox, and unknown.

11. The information handling system of claim 10, where the type Ti is the checkbox which classifies a redaction block area located over a group of labels in the document.

12. The information handling system of claim 9, where each redaction block area is a blacked-out area in the document.

13. The information handling system of claim 9, where the set of instructions are executable to detect location information by computing a geometric shape and x, y coordinates for each redaction block area.

14. The information handling system of claim 9, where the set of instructions are executable to perform actions of:

applying, by the system, optical character recognition to the document to detect text fragments in the document;

detecting, by the system, location information for each text fragment identified in the document; and

mapping, by the system, each redaction block area to any associated text fragments in the document based on the location information for each redaction block area and text fragment in the document.

15. The information handling system of claim 9, where the set of instructions are executable to insert, by the system, a sentinel string of predetermined characters into the document for each detected redaction block area.

16. The information handling system of claim 9, where the set of instructions are executable to analyze the document by applying a redaction block detection process to scan each line of the image file to identify any redacted text blocks by locating a threshold number T1 of consecutive black pixels that are aligned in a threshold number T1 of consecutive rows.

17. A computer program product stored in a computer readable storage medium, comprising computer instructions that, when executed by an information handling system, causes the system to automatically detecting redaction blocks in a document by performing actions comprising:

receiving, by the system, the document as an image file;

analyzing, by the information handling system, the document to identify any redaction blocks in the document;

detecting, by the information handling system, location information for each redaction block identified in the document;

classifying, by the system, each identified redaction block as a redaction block type Ti selected from a group consisting of a text block, a table cell, a checkbox, and unknown; and

generating, by the system, an output file which identifies, for the document, each text fragment and associated text fragment location information, along with each redaction block and associated redaction block fragment location information and redaction block type Ti.

18. The computer program product of claim 17, further comprising computer instructions that, when executed by the information handling system, causes the system to perform actions comprising:

applying, by the system, optical character recognition to the document to detect text fragments in the document;

detecting, by the system, location information for each text fragment identified in the document; and

mapping, by the system, each redaction block to any associated text fragments in the document based on the location information for each redaction block and text fragment in the document.

19. The computer program product of claim 17, further comprising computer instructions that, when executed by the information handling system, causes the system to insert a sentinel string of predetermined characters into the document for each detected redaction block.

20. The computer program product of claim 17, where analyzing the document comprises applying a redaction block detection process to scan each line of the image file to identify any redacted text blocks by locating a threshold number T1 of consecutive black pixels that are aligned in a threshold number T1 of consecutive rows.