Identification of emphasized text in electronic documents

Patent metadata

Field	Value
Publication number	US-10169650-B1
Application number	US-201715639831-A
Country	US
Kind code	B1
Filing date	Jun 30, 2017
Priority date	Jun 30, 2017
Publication date	Jan 1, 2019
Grant date	Jan 1, 2019

Abstract

To identify emphasized text, bounding boxes are based on clusters resulting from horizontal compression and horizontal morphological dilation. The bounding boxes are processed to determine if any contain words or characters in bold. A bounding box is eliminated based on a comparison of its density and an average density across all bounding boxes. If its density is greater, text elements within the bounding box are evaluated to determine whether the text element is bold.

First claim

What is claimed is:

1. A method of identifying emphasized text, the method comprising:
performing horizontal compression on an input image to generate a horizontally compressed image, the input image comprising lines of text, each line of text comprising a plurality of words or characters;
performing horizontal morphological dilation on the compressed image to form a horizontally dilated image, the horizontally dilated image comprising clusters, each cluster corresponding to a different one of the lines of text;
calculating a bounding box for each cluster, resulting in a plurality of bounding boxes;
calculating a first average density, the first average density calculated across all the bounding boxes;
for each of the bounding boxes, comparing the first average density to a density of the bounding box; and
identifying a specific bounding box, from among the plurality of bounding boxes, as having a word or character in bold, the identifying based on the comparison of the first average density to the density of the specific bounding box.

2. The method of claim 1 , wherein the bounding boxes, for calculating the first average density, are on the horizontally compressed image.

3. The method of claim 1 , wherein:
each bounding box includes upper and lower zones, at least one of which contains a fractional part of a word or a character, and
none of the upper zones and none of the lower zones are used in the calculating of the first average density.

4. The method of claim 1 , further comprising detecting an underline from the compressed image, wherein the bounding boxes, for calculating the first average density, exclude the underline.

5. The method of claim 1 , wherein the specific bounding box contains a plurality of text elements, the text elements are words or characters, the specific bounding box is divided by text element areas, each text element area covers a different one of the text elements, and the method further comprises:
calculating a second average density, the second average density calculated across all text element areas in the specific bounding box;
for each text element area, comparing the second average density to a density of the text element area; and
identifying a specific text element, from among a plurality of text elements, as being in bold, the identifying based on the comparison of the second average density to the density of the text element area containing the specific text element.

6. The method of claim 5 , wherein the text element areas, for calculating the second average density, are on the input image.

7. The method of claim 5 , wherein the text element areas, for calculating the second average density, are on the horizontally compressed image.

8. The method of claim 5 , wherein:
each text element area includes upper and lower zones, at least one of which contains a fractional part of one or more of the text elements, and
none of the upper zones and none of the lower zones are used in the calculating of the second average density.

9. The method of claim 5 , wherein:
the specific bounding box includes an underline, and
the text element areas, for calculating the second average density, exclude the underline.

10. The method of claim 1 , further comprising generating an output image, wherein the output image includes a tag that distinguishes an area within the specific bounding box as having a word or character in bold, the tag distinguishes the area from other areas of the input image which have neither a word nor character in bold.

11. A system of identifying emphasized text, the system comprising:
a processor; and
a memory device in communication with the processor, the memory device storing instructions,
wherein the processor is configured to perform a process to identify emphasized text according to the stored instructions, and the process comprises:
performing horizontal compression on an input image to generate a horizontally compressed image, the input image comprising lines of text, each line of text comprising a plurality of words or characters;
performing horizontal morphological dilation on the compressed image to form a horizontally dilated image, the horizontally dilated image comprising clusters, each cluster corresponding to a different one of the lines of text;
calculating a bounding box for each cluster, resulting in a plurality of bounding boxes;
calculating a first average density, the first average density calculated across all the bounding boxes;
for each of the bounding boxes, comparing the first average density to a density of the bounding box; and
identifying a specific bounding box, from among the plurality of bounding boxes, as having a word or character in bold, the identifying based on the comparison of the first average density to the density of the specific bounding box.

12. The system of claim 11 , wherein the bounding boxes, for calculating the first average density, are on the horizontally compressed image.

13. The system of claim 11 , wherein:
each bounding box includes upper and lower zones, at least one of which contains a fractional part of a word or a character, and
none of the upper zones and none of the lower zones are used in the calculating of the first average density.

14. The system of claim 11 , wherein the process further comprises detecting an underline from the compressed image, and the bounding boxes, for calculating the first average density, exclude the underline.

15. The system of claim 11 , wherein the specific bounding box contains a plurality of text elements, the text elements are words or characters, the specific bounding box is divided by text element areas, each text element area covers a different one of the text elements, and the process further comprises:
calculating a second average density, the second average density calculated across all text element areas in the specific bounding box;
for each text element area, comparing the second average density to a density of the text element area; and
identifying a specific text element, from among a plurality of text elements, as being in bold, the identifying based on the comparison of the second average density to the density of the text element area containing the specific text element.

16. The system of claim 15 , wherein the text element areas, for calculating the second average density, are on the input image.

17. The system of claim 15 , wherein the text element areas, for calculating the second average density, are on the horizontally compressed image.

18. The system of claim 15 , wherein:
each text element area includes upper and lower zones, at least one of which contains a fractional part of one or more of the text elements, and
none of the upper zones and none of the lower zones are used in the calculating of the second average density.

19. The system of claim 15 , wherein:
the specific bounding box includes an underline, and
the text element areas, for calculating the second average density, exclude the underline.

20. The system of claim 11 , wherein the process further comprises generating an output image, the output image includes a tag that distinguishes an area within the specific bounding box as having a word or character in bold, the tag distinguishes the area from other areas of the input image which have neither a word nor character in bold.

21. A non-transitory computer-readable medium having stored thereon computer readable instructions that, when executed by a processor of a system, cause the s

Assignees

• Konica Minolta Laboratory Usa Inc

Inventors

• Ming Wei

Classifications

• G06V30/414

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

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06V10/273

  removing elements interfering with the pattern to be recognised · CPC title

• G06V10/34

  Smoothing or thinning of the pattern; Morphological operations; Skeletonisation · CPC title