Inferring stroke information from an image

Patent metadata

Field	Value
Publication number	US-10163004-B2
Application number	US-201715474512-A
Country	US
Kind code	B2
Filing date	Mar 30, 2017
Priority date	Mar 30, 2017
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box including a first set of the plurality of character segments and a second character bounding box including a second set of the plurality of character segments; determining an ordering for the first set based on a plurality of texture properties for the first set; determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

First claim

What is claimed is:

1. A method for character recognition, comprising:
obtaining a plurality of character segments extracted from an image;
determining a first character bounding box comprising a first set of the plurality of character segments and a second character bounding box comprising a second set of the plurality of character segments;
determining an ordering for the first set based on a plurality of texture properties for the first set;
determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and
executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

2. The method of claim 1 , further comprising:
determining a plurality of directions of the second set and a timing property for the second set; and
executing character recognition for the second character bounding box by sending the second set, the plurality of directions of the second set, and the timing property for the second set to the ICR engine,
wherein the plurality of character segments are extracted from the image by a skeletonizer, and
wherein the plurality of character segments form a single text line in the image.

3. The method of claim 1 , wherein determining the ordering comprises:
locating an intersection of a first character segment and a second character segment in the first set;
determining an intersection texture property;
comparing the intersection texture property with a texture property of the first character segment and with a texture property of the second character segment; and
determining the first character segment was drawn before the second character segment in response to the intersection texture property matching the texture property of the second character segment.

4. The method of claim 3 , wherein the texture property is a color.

5. The method of claim 3 , wherein the texture property is a fill pattern.

6. The method of claim 1 , wherein determining the plurality of directions comprises:
determining a first endpoint and a second endpoint of a character segment in the first set;
comparing a brush width of the first endpoint with a brush width of the second endpoint; and
determining the first endpoint is the starting endpoint in response to brush width of the first endpoint exceeding the brush width of the second endpoint.

7. The method of claim 1 , wherein determining the plurality of directions comprises:
determining a first endpoint and a second endpoint of a character segment in the first set;
comparing an intensity of the first endpoint with an intensity of the second endpoint; and
determining the first endpoint is the starting endpoint in response to intensity of the first endpoint exceeding the intensity of the second endpoint.

8. The method of claim 1 , wherein determining the ordering comprises:
calculating a first angle between the vertical and a first character segment in the first set;
calculating a second angle between the vertical and a second character segment in the first set; and
determining the first character segment was drawn before the second character segment in response to the first angle being smaller than the second angle.

9. The method of claim 1 , further comprising determining a drawing duration for the first set by:
resetting a clock value for the first character bounding box;
calculating a first length of a first character segment in the first set;
incrementing the clock value for the first character segment based on the first length;
calculating a second length of a second character segment in the first set; and
incrementing the clock value for the second character segment based on the second length,
wherein the drawing duration for the first set is the clock value, and
wherein the drawing duration for the first set is sent to the ICR engine.

10. The method of claim 9 , further comprising:
selecting a first velocity for the first character segment based on the first length, wherein incrementing the clock value for the first character segment is further based on the first velocity; and
selecting a second velocity for the second character segment based on the second length, wherein incrementing the clock value for the second character segment is further based on the second velocity.

11. The method of claim 1 , further comprising:
generating an editable electronic document comprising recognized characters outputted by the ICR engine.

12. A system for character recognition, comprising:
a memory;
a computer processor connected to the memory and that:
obtains a plurality of character segments extracted from an image;
determines a first character bounding box comprising a first set of the plurality of character segments and a second character bounding box comprising a second set of the plurality of character segments;
determines an ordering for the first set based on a plurality of texture properties for the first set;
determines a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and
executes character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

13. The system of claim 12 , wherein determining the ordering comprises:
locating an intersection of a first character segment and a second character segment in the first set;
determining an intersection texture property;
comparing the intersection texture property with a texture property of the first character segment and with a texture property of the second character segment; and
determining the first character segment was drawn before the second character segment in response to the intersection texture property matching the texture property of the second character segment.

14. The system of claim 12 , wherein determining the plurality of directions comprises:
determining a first endpoint and a second endpoint of a character segment in the first set;
comparing a brush width of the first endpoint with a brush width of the second endpoint; and
determining the first endpoint is the starting endpoint in response to brush width of the first endpoint exceeding the brush width of the second endpoint.

15. The system of claim 12 , wherein determining the plurality of directions comprises:
determining a first endpoint and a second endpoint of a character segment in the first set;
comparing an intensity of the first endpoint with an intensity of the second endpoint; and
determining the first endpoint is the starting endpoint in response to intensity of the first endpoint exceeding the intensity of the second endpoint.

16. The system of claim 12 , wherein the computer processor also generates an editable electronic document comprising recognized characters outputted by the ICR engine.

17. A non-transitory computer readable medium (CRM) storing computer program code executed by a computer processor that:
obtains a plurality of character segments extracted from an image;
determines a first character bounding box comprising a first set of the plurality of character segments and a second character bounding box comprising a second set of the plurality of character segments;
determines an ordering for the first set based on a plurality of texture properties f

Assignees

• Konica Minolta Laboratory Usa Inc

Inventors

• Guarnieri Stuart
• Grams Jason James

Classifications

• G06V30/15

  Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques · CPC title

• G06V30/347 Primary

  Sampling; Contour coding; Stroke extraction · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/344

  Physics · mapped topic

• G06K2209/01

  Physics · mapped topic