OPTICAL CHARACTER RECOGNITION OF CONNECTED CHARACTERS

• US 20190332860A1
• Filed: 04/25/2018
• Published: 10/31/2019
• Est. Priority Date: 04/25/2018
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: Salameh, Tariq Mohammad
• Granted Patent: US 10,719,701 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 5/30 Erosion or dilatation, e.g. thinning
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 10/30 Noise filtering
• CPC Class Codes: G06V 10/32 Normalisation of the pattern dimensions
• CPC Class Codes: G06V 30/153 using recognition of characters or words
• CPC Class Codes: G06V 30/158 using character size, text spacings or pitch estimation
• CPC Class Codes: G06V 30/293 of characters other than Kanji, Hiragana or Katakana
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

Implementations for optical character recognition of a language script can include actions of receiving an image comprising a graphical representation of a word written in the language script, segmenting the word into two or more segments, each segment being determined based on one or more of a variation in a height of the word and a variation in a width of the word, and including at least one character, providing a boundary for each segment of the two or more segments, the boundary enclosing the at least one character of a respective segment, each boundary having an edge with respect to an axis of the image, normalizing boundaries of the two or more segments by aligning edges of the boundaries, and labeling each segment of the two or more segments with a respective label, the respective label indicating a language character within the respective boundary.

Claims

1. A computer-implemented method for optical character recognition of a language script, the method being executed by one or more processors, the method comprising:

receiving, by the one or more processors, an image comprising a graphical representation of a word written in the language script;

segmenting, by the one or more processors, the word into two or more segments, each segment being determined based on one or more of a variation in a height of the word and a variation in a width of the word, and comprising at least one character;

providing, by the one or more processors, a boundary for each segment of the two or more segments, the boundary enclosing the at least one character of a respective segment, each boundary having an edge with respect to an axis of the image;

normalizing, by the one or more processors, boundaries of the two or more segments by aligning edges of the boundaries; and

labeling, by the one or more processor, each segment of the two or more segments with a respective label, the respective label indicating a language character within the respective boundary.

2. The method of claim 1, further comprising, prior to segmenting, filtering the image to remove noise.

3. The method of claim 1, further comprising, prior to segmenting, scaling the image.

4. The method of claim 1, further comprising, prior to segmenting, applying a morphology filter to transform the image.

5. The method of claim 1, further comprising adjusting the boundary of each segment to normalize pixel size across segments.

6. The method of claim 5, wherein normalizing comprises scaling at least one boundary, scaling comprising one of shrinking using an inter-area algorithm, and enlarging using an inter-cubic algorithm.

7. The method of claim 1, wherein the edges of the boundaries are aligned.

8. The method of claim 1, wherein the language script comprises Arabic script, and the language character comprises an Arabic character.

9. The method of claim 1, wherein each segment includes a single character only.

10. The method of claim 1, further comprising determining one or more of a height of the boundary and a width of the boundary.

11. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for optical character recognition of a language script, the operations comprising:

receiving an image comprising a graphical representation of a word written in the language script;

segmenting the word into two or more segments, each segment being determined based on one or more of a variation in a height of the word and a variation in a width of the word, and comprising at least one character;

providing a boundary for each segment of the two or more segments, the boundary enclosing the at least one character of a respective segment, each boundary having an edge with respect to an axis of the image;

normalizing boundaries of the two or more segments by aligning edges of the boundaries; and

labeling each segment of the two or more segments with a respective label, the respective label indicating a language character within the respective boundary.

12. The computer-readable storage medium of claim 11, wherein operations further comprise, prior to segmenting, filtering the image to remove noise.

13. The computer-readable storage medium of claim 11, wherein operations further comprise, prior to segmenting, scaling the image.

14. The computer-readable storage medium of claim 11, wherein operations further comprise, prior to segmenting, applying a morphology filter to transform the image.

15. The computer-readable storage medium of claim 11, wherein operations further comprise adjusting the boundary of each segment to normalize pixel size across segments.

16. The computer-readable storage medium of claim 15, wherein normalizing comprises scaling at least one boundary, scaling comprising one of shrinking using an inter-area algorithm, and enlarging using an inter-cubic algorithm.

17. The computer-readable storage medium of claim 11, wherein the edges of the boundaries are aligned.

18. The computer-readable storage medium of claim 11, wherein the language script comprises Arabic script, and the language character comprises an Arabic character.

19. The computer-readable storage medium of claim 11, wherein each segment includes a single character only.

20. The computer-readable storage medium of claim 11, wherein operations further comprise determining one or more of a height of the boundary and a width of the boundary.

21. A system, comprising:

a computing device; and

a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for optical character recognition of a language script, the operations comprising;

receiving an image comprising a graphical representation of a word written in the language script,

segmenting the word into two or more segments, each segment being determined based on one or more of a variation in a height of the word and a variation in a width of the word, and comprising at least one character,

providing a boundary for each segment of the two or more segments, the boundary enclosing the at least one character of a respective segment, each boundary having an edge with respect to an axis of the image,

normalizing boundaries of the two or more segments by aligning edges of the boundaries, and

labeling each segment of the two or more segments with a respective label, the respective label indicating a language character within the respective boundary.

22. The system of claim 21, wherein operations further comprise, prior to segmenting, filtering the image to remove noise.

23. The system of claim 21, wherein operations further comprise, prior to segmenting, scaling the image.

24. The system of claim 21, wherein operations further comprise, prior to segmenting, applying a morphology filter to transform the image.

25. The system of claim 21, wherein operations further comprise adjusting the boundary of each segment to normalize pixel size across segments.

26. The system of claim 25, wherein normalizing comprises scaling at least one boundary, scaling comprising one of shrinking using an inter-area algorithm, and enlarging using an inter-cubic algorithm.

27. The system of claim 21, wherein the edges of the boundaries are aligned.

28. The system of claim 21, wherein the language script comprises Arabic script, and the language character comprises an Arabic character.

29. The system of claim 21, wherein each segment includes a single character only.

30. The system of claim 21, wherein operations further comprise determining one or more of a height of the boundary and a width of the boundary.