Character recognition

• US 8,750,619 B2
• Filed: 12/27/2013
• Issued: 06/10/2014
• Est. Priority Date: 04/08/2010
• Status: Expired due to Fees

• Current Assignee: University of Calcutta
• Original Assignee: University of Calcutta
• Inventors: Chaki, Nabendu, Shaikh, Soharab Hossain
• Primary Examiner(s): Do, Anh
• Application Number:
  US14/142,209
• Publication Number:
  US 20140112582A1
• Time in Patent Office: 165 Days
• Field of Search: 382/173, 382/177, 382/178, 382/179, 382/181, 382/187, 382/199, 382/203, 382/204, 250/202, 463/1, 463/24, 463/29
• US Class Current: 382/187
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/148 Segmentation of character regions
• CPC Class Codes: G06V 30/153 using recognition of characters or words
• CPC Class Codes: G06V 30/184 by analysing segments intersecting the pattern

Abstract

Systems and methods for character recognition by performing lateral view-based analysis on the character data and generating a feature vector based on the lateral view-based analysis.

Claims

1. A device comprising:

a data acquisition device configured to acquire character data comprising one or more characters, the one or more characters having a first contour and a second contour; and

a computing device configured to;

perform lateral view analysis on the character data, the lateral view analysis comprising locating characteristic points on the first and second contours, including dividing the one or more characters into segments of more than one size, wherein a characteristic point is located in each segment on the first contour and the second contour;

identify the one or more characters based on the lateral view analysis.

2. The device of claim 1,

wherein the segments and the characteristic points are equal in number;

and

wherein a number of characteristic points at relatively lower portions of the one or more characters is greater than a number of characteristic points at relatively higher portions of the one or more characters.

3. The device of claim 1, wherein the device is a mobile device.

4. The device of claim 1, wherein the device is a smartphone.

5. The device of claim 1,

wherein performing the lateral view analysis on the character data includes locating characteristic points on the first and second contours of a character of the one or more characters, including dividing the character into segments of more than one size, wherein a characteristic point is located in each segment on the first contour and the second contour of the character;

wherein the computing device is further configured to generate a feature vector of the character based on the lateral view analysis;

wherein identifying the one or more characters includes identifying the character based on the feature vector; and

wherein the feature vector comprises;

a minimum distance of characteristic points on the first contour of the character;

a maximum distance of characteristic points on the second contour of the character;

a width of the character; and

a height of the character.

6. The device of claim 1, wherein the one or more characters comprise characters of a language script written vertically.

7. The device of claim 1, wherein the one or more characters comprise characters of a language that uses Matra.

8. A device comprising:

a data acquisition device configured to acquire character data comprising one or more compound characters; and

a computing device configured to;

divide each of the one or more compound characters diagonally into two or more component characters, each of the two or more component characters having a first contour and a second contour;

perform lateral view analysis on character data of the two or more component characters from the character data of the one or more compound characters, the lateral view analysis comprising locating characteristic points on the first and second contours of each of the two or more component characters, including dividing the two or more component characters into segments, wherein a characteristic point is located in each segment on the first contour and the second contour;

identify the two or more component characters based on the lateral view analysis; and

identify the one or more compound characters from the identified two or more component characters.

9. The device of claim 8,

wherein the segments and the characteristic points are equal in number;

and

wherein a number of characteristic points at relatively lower portions of the two or more component characters is greater than a number of characteristic points at relatively higher portions of the two or more component characters.

10. The device of claim 8, wherein the device is a mobile device.

11. The device of claim 8, wherein the device is a smartphone.

12. The device of claim 8,

wherein performing the lateral view analysis on the character data of the two or more component characters includes locating characteristic points on the first and second contours of first and second component characters of the two or more component characters, including dividing each of the first and second component characters into segments, wherein a characteristic point is located in each segment on the first contour and the second contour of each of the first and second component characters;

wherein the computing device is further configured to generate a feature vector of each of the first and second component characters based on the lateral view analysis;

wherein identifying the first and second component characters is based on the feature vector of each of the first and second component characters, respectively; and

wherein each of the feature vectors comprises;

a minimum distance of characteristic points on the first contour of the component character corresponding to the feature vector;

a maximum distance of characteristic points on the second contour of the corresponding component character;

a width of the corresponding component character; and

a height of the corresponding component character.

13. The device of claim 8, wherein the one or more compound characters comprise compound characters of a language script written vertically.

14. The device of claim 8, wherein the one or more compound characters comprise compound characters of a language that uses Matra.

15. A method comprising:

receiving, by a device, character data comprising one or more characters;

performing, by the device, lateral view analysis on the character data, including dividing the one or more characters into segments of more than one size; and

identifying, by the device, the one or more characters based on the lateral view analysis.

16. The method of claim 15, wherein the one or more characters have a first contour and a second contour;

wherein performing lateral analysis further comprises locating characteristic points on the first and second contours; and

wherein a characteristic point is located in each segment on the first contour and the second contour.

17. The method of claim 15,

wherein the one or more characters have a first contour and a second contour;

wherein performing lateral analysis further comprises locating characteristic points on the first and second contours, wherein a characteristic point is located in each segment on the first contour and the second contour;

wherein the segments and the characteristic points are equal in number; and

wherein a number of characteristic points at relatively lower portions of the one or more characters is greater than a number of characteristic points at relatively higher portions of the one or more characters.

18. The method of claim 15, wherein the device is a mobile device.

19. The method of claim 15, wherein the device is a smartphone.

20. The method of claim 15,

wherein the one or more characters have a first contour and a second contour;

wherein performing the lateral view analysis on the character data comprises;

locating characteristic points on the first and second contours of a character of the one or more characters; and

dividing the character into segments of more than one size, wherein a characteristic point is located in each segment on the first contour and the second contour of the character;

wherein the method further comprises;

generating, by the device, a feature vector of the character based on the lateral view analysis;

wherein identifying the one or more characters includes identifying the character based on the feature vector; and

wherein the feature vector comprises;

a minimum distance of characteristic points on the first contour of the character;

a maximum distance of characteristic points on the second contour of the character;

a width of the character; and

a height of the character.

21. The method of claim 15, wherein the one or more characters comprise characters of a language script written vertically.

22. The method of claim 15, wherein the one or more characters comprise characters of a language that uses Matra.