Granted Patent B1

US 10,049,097 · App. 15/417,272 · Granted Aug 14, 2018

Inventors: Sainarayanan Gopalakrishnan (Chennai, IN); Rajasekar Kanagasabai (Chennai, IN); Sudhagar Subbaian (Coimbatore, IN)

Assignee: XEROX CORPORATION

G06F17/248G06F17/2755G06K9/72G06K2209/01

Abstract

Claims (59)

1. A method for creating a multi-layered Optical Character Recognition (OCR) document, the method comprising:

receiving a scanned image corresponding to a document, the document includes text information;

generating a binary image from the scanned image;

performing a morphological dilation operation to create one or more text groups, using a horizontal structuring element and a vertical structuring element;

applying OCR on each text group to generate a corresponding OCR layer;

combining the one or more OCR layers while creating a multi-layered OCR document; and

superimposing the combined OCR layers as invisible text layers over the scanned image to create the multi-layered OCR document, the multi-layered OCR document facilitates selection of a text group corresponding to the OCR layer.

2. The method as claimed in claim 1 , wherein the applying OCR further comprises: extracting text information corresponding to the one or more text groups.

3. The method as claimed in claim 1 , further comprising scanning the document using an OCR option.

4. The method as claimed in claim 1 , wherein the multi-layered OCR document is a PDF document.

5. The method as claimed in claim 1 , wherein the one or more text groups are created by merging one or more nearby adjacent text information.

6. The method as claimed in claim 1 , wherein the performing the morphological dilation operation comprises:

dilating the binary image using the horizontal structuring element for merging one or more nearby adjacent text information along a horizontal axis; and

dilating the horizontally dilated image with the vertical structuring element for merging one or more nearby adjacent text information along a vertical axis.

7. The method as claimed in claim 6 , wherein the horizontal structuring element has a shorter width with respect to text size, so as to prevent merging of one or more farther adjacent text information along the horizontal axis.

8. The method as claimed in claim 6 , wherein the vertical structuring element has a larger height with respect to text size, so as to enable merging of one or more nearby adjacent text regions along the vertical axis.

9. The method as claimed in claim 1 further comprising assigning a unique color to each OCR layer of the multi-layered OCR document.

10. The method as claimed in claim 9 , further comprising displaying the multi-layered OCR document with the unique color assigned to each OCR layer.

11. A method for creating an editable and searchable document, comprising:

receiving a document for scanning by a user, the document includes text;

creating a scanned image of the document;

converting the scanned image into a binary image;

creating one or more text groups using a morphological dilation operation, wherein the operation comprises:

dilating the binary image using a horizontal structuring element for merging one or more nearby adjacent text information along a horizontal axis; and

dilating the horizontally dilated image with a vertical structuring element for merging one or more nearby adjacent text information along a vertical axis;

creating an OCR (Optical Character Recognition) layer for each text group;

combining the one or more OCR layers for the one or more text groups; and

combining the combined OCR layers and scanned image to create the editable and searchable document, facilitating selection of a portion of text by the user.

12. The method as claimed in claim 11 , wherein the text in the document is arranged in the form of one or more columns and one or more rows.

13. The method as claimed in claim 11 , further comprising generating a color coding scheme for each text group, facilitating easy selection of the corresponding text group by the user.

14. The method as claimed in claim 11 , wherein the horizontal structuring element is selected to have a lesser width with respect to text size, and the vertical structuring element is selected to have a larger height with respect to text size.

15. A multi-function device for generating a multi-layered Optical Character Recognition (OCR) file, comprising:

a scanning module configured to:

receive a document for scanning using OCR option; and

generate a scanned image;

a multi-layered OCR document generation module configured to:

generate a binary image from the scanned image;

perform a morphological dilation operation on the binary image to create one or more text groups;

apply OCR on each text group to create the corresponding OCR layer; and

combine the one or more OCR layers while creating the multi-layered OCR file, wherein the multi-layered OCR file allows a user to select a portion of text from the multi-layered OCR file.

16. The multi-function device as claimed in claim 15 , wherein the multi-layered OCR document generation module is configured to:

dilate the binary image with a horizontal structuring element for merging one or more nearby adjacent text regions along a horizontal axis, wherein the horizontal structuring element has a shorter width with respect to text size in order to prevent merging of one or more farther adjacent text information along the horizontal axis; and

dilate the horizontally dilated processed image with a vertical structuring element for merging one or more nearby adjacent text regions along a vertical axis, wherein the vertical structuring element has a larger height with respect to text size in order to enable merging of one or more nearby adjacent text regions along the vertical axis.

17. The multi-function device as claimed in claim 15 , wherein the multi-layered OCR document generation module is further configured to assign a unique color to each OCR layer of the multi-layered OCR file.

18. The multi-function device as claimed in claim 15 , wherein the multi-layered OCR document generation module is further configured to superimpose the combined OCR layers over the scanned image to generate a PDF file.

19. The multi-function device as claimed in claim 15 , wherein the multi-layered OCR document generation module is further configured to remove one or more lines of the binary image.

20. A system comprising:

a scanner configured to:

scan a document to generate a scanned image, the document having text information; and

a computing device in communication with the scanner, wherein the computing device comprises a multi-layered OCR (Optical Character Recognition) document generation module, configured to:

receive the scanned image from the scanner;

generate a binary image from the scanned image;

perform a morphological dilation operation on the binary image to create one or more text groups using a horizontal structuring element and a vertical structuring element;

apply OCR on each text group to create the corresponding OCR layer;

combine the one or more OCR layers while creating a multi-layered OCR file; and

superimpose the combined OCR layers over the scanned image to generate the multi-layered OCR file, wherein the multi-layered OCR file allows a user to select a portion of text from the multi-layered OCR file.

21. The system as claimed in claim 20 , wherein the multi-layered OCR document generation module is configured to:

dilate the binary image with the horizontal structuring element for merging one or more nearby adjacent text regions along a horizontal axis, wherein the horizontal structuring element has a shorter width with respect to text size in order to prevent merging of one or more farther adjacent text information along the horizontal axis; and

dilate the horizontally dilated processed image with the vertical structuring element for merging one or more nearby adjacent text regions along a vertical axis, wherein the vertical structuring element has a larger height with respect to text size in order to enable merging of one or more nearby adjacent text regions along the vertical axis.

Assignments (9)

Cited By (2)

US 12,374,148 US 12,469,320