Detecting a junction in a text line of CJK characters

• US 8,989,485 B2
• Filed: 10/14/2013
• Issued: 03/24/2015
• Est. Priority Date: 04/27/2012
• Status: Expired due to Fees

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY Development LLC
• Inventors: Chulinin, Yuri, Senkevich, Oleg
• Primary Examiner(s): Dang, Duy M
• Application Number:
  US14/053,208
• Publication Number:
  US 20140126812A1
• Time in Patent Office: 526 Days
• Field of Search: 382/170, 382/165
• US Class Current: 382/165
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/15 Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques
• CPC Class Codes: G06V 30/18095 Summing image-intensity values; Projection and histogram analysis
• CPC Class Codes: G06V 30/18181 Graphical representation, e.g. directed attributed graph
• CPC Class Codes: G06V 30/293 of characters other than Kanji, Hiragana or Katakana
• CPC Class Codes: G06V 40/107 Static hand or arm

Abstract

A method for detecting a junction in a received image of the line of text to update a junction list with descriptive data is provided. The method includes creating a color histogram based on a number of color pixels in the received image of the line of text and detecting, based at least in part on the received image of the line of text, a rung within the received image of the line of text. The method also includes identifying a horizontal position of the detected rung in the received image of the line of text and identifying a gateway on the color histogram, wherein the identified gateway is associated with the detected rung. The junction list is updated with data including a description of the identified gateway.

Claims

1. A method for detecting a junction in a received image of a line of text to update a junction list with descriptive data, the method comprising:

creating a color histogram based on a number of color pixels in the received image of the line of text;

detecting, based at least in part on the received image of the line of text, a rung within the received image of the line of text;

identifying a horizontal position of the detected rung in the received image of the line of text;

additionally identifying a gateway on the color histogram, wherein the identified gateway is associated with the detected rung; and

updating the junction list with data including a description of the identified gateway.

2. The method of claim 1, wherein creating the color histogram further comprises summing the number of color pixels in a straight horizontal line of the received image of the line of text.

3. The method of claim 1, wherein detecting the rung further comprises detecting a difference in thickness and position of the horizontal or almost horizontal strokes of the symbols in the received image of the line of text.

4. The method of claim 1, wherein identifying the horizontal position further comprises dividing the received image of the line of text into three horizontal regions comprising a bottom stripe, a middle stripe, and a top stripe.

5. The method of claim 4, wherein identifying the horizontal position further comprises identifying that the detected rung is positioned in the bottom stripe or the middle stripe.

6. The method of claim 1, wherein identifying the gateway further comprises identifying a plateau on the created color histogram, wherein the plateau corresponds to a low level on the created color histogram.

7. The method of claim 6, wherein identifying the plateau further comprises detecting a peak on each side of the plateau on the created color histogram.

8. The method of claim 1, further comprising calculating a pixel distance from a start of the received image of the line of text to the identified gateway.

9. A system for detecting a junction in a received image of a line of text to update a junction list with descriptive data, the system comprising:

a memory configured to store processor-executable instructions; and

a processor operatively coupled to the memory, wherein the processor is configured to;

create a color histogram based on a number of color pixels in the received image of the line of text;

detect, based at least in part on the received image of the line of text, a rung in the received image of the line of text;

identify a horizontal position of the detected rung in the received image of the line of text;

additionally identify a gateway on the color histogram, wherein the identified gateway is associated with the detected rung; and

update the junction list with data including a description of the identified gateway.

10. The system of claim 9, wherein the created color histogram is a quantity of color pixels in a straight horizontal line of the received image of the line of text.

11. The system of claim 9, wherein the detected rung is a portion of the received image of the line of text where two neighbor characters are joined.

12. The system of claim 9, wherein the horizontal position corresponds to one of three horizontal regions of the received image of the line of text, wherein the three horizontal regions comprise a bottom stripe, a middle stripe, and a top stripe.

13. The system of claim 12, wherein the horizontal position of the detected rung is in the bottom stripe or the middle stripe.

14. The system of claim 9, wherein identification of the identified gateway is based at least in part on identification of a plateau on the created color histogram, and wherein the plateau corresponds to a low level on the created color histogram.

15. The system of claim 14, wherein the processor is configured to detect a peak on each side of the plateau on the created color histogram.

16. The system of claim 9, wherein the description of the identified gateway includes a pixel distance from a start of the received image of the line of text to the identified gateway.

17. A non-transitory computer-readable storage medium having computer-readable instructions stored therein, the instructions being executable by a processor of a computing system, wherein the instructions comprise:

instructions to create a color histogram based on a number of color pixels in a received image of a line of text;

instructions to detect, based at least in part on the received image of the line of text, a rung in the received image of the line of text;

instructions to identify a horizontal position of the detected rung in the received image of the line of text;

instructions to identify a gateway on the created color histogram associated with the detected rung; and

instructions to update a junction list with data including a description of the identified gateway.

18. The non-transitory computer-readable storage medium of claim 17, wherein the created color histogram is a quantity of color pixels in a straight horizontal line of the received image of the line of text.

19. The non-transitory computer-readable storage medium of claim 17, further comprising instructions to identify a plateau on the created color histogram, wherein the plateau corresponds to a low level on the created color histogram, and wherein the identified gateway is identified based at least in part on the plateau.

20. The non-transitory computer-readable storage medium of claim 19, further comprising instructions to detect a peak on each side of the plateau on the created color histogram.