CHARACTER RECOGNITION

• US 20110249897A1
• Filed: 04/08/2010
• Published: 10/13/2011
• Est. Priority Date: 04/08/2010
• Status: Active Grant

• Current Assignee: University of Calcutta
• Original Assignee: University of Calcutta
• Inventors: Shaikh, Soharab Hossain, CHAKI, Nabendu
• Granted Patent: US 8,391,602 B2
• Time in Patent Office: Days
• US Class Current: 382/177
• 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 method comprising:

acquiring character data comprising one or more characters, the one or more characters having a first contour and a second contour;

performing lateral view analysis on the character data;

generating a feature vector based on the lateral view analysis; and

identifying the one or more characters.

2. The method of claim 1, wherein performing lateral analysis comprises

selecting a number of characteristic points;

dividing the one or more characters into a number of horizontal segments, the number of segments equal to the number of characteristic points; and

locating characteristic points on the first and second contours, wherein a characteristic point is located in each segment on both the first and second contours.

3. The method of claim 2, wherein an origin is located at a lower left of the one or more characters and wherein the characteristic points on the first contour are located at a minimum distance from a vertical axis rising from the origin and the characteristic points on the second contour are located at a maximum distance from the vertical axis.

4. The method of claim 2, wherein the horizontal segments have the same height.

5. The method of claim 1, further comprising binarizing the character data.

6. The method of claim 1, further comprising removing noise from the character data.

7. The method of claim 1, further comprising performing oblique/skew detection.

8. The method of claim 1, further comprising segmenting the character data into individual characters, the character data comprising a plurality of characters.

9. The method of claim 1, wherein the contour data is not thinned.

10. The method of claim 1, wherein identifying the one or more characters comprises using an artificial neural network.

11. The method of claim 1, wherein the method is adapted to recognize cursive characters.

12. The method of claim 1, wherein the method is substantially font invariant.

13. The method of claim 1, wherein the method is configured to identify characters in fonts having variable character widths.

14. The method of claim 1, wherein the feature vector comprises the minimum distance of the characteristic points on the first contour, the maximum distances of the characteristic points on the second contour, the width of the character, and the height of the character.

15. A system comprising a microprocessor and a memory, the memory comprising computer executable instructions for:

acquiring character data comprising one or more characters, the one or more characters having a first contour and a second contour;

performing lateral view analysis on the character data;

generating a feature vector based on the lateral view analysis; and

identifying the one or more characters.

16. The system of claim 15, further comprising a data acquisition device.

17. The system of claim 15, further comprising computer executable instructions for binarizing the character data, removing noise from the character data, and performing oblique/skew detection.

18. The system of claim 15, further comprising computer executable instructions for segmenting the character data into individual characters.

19. The system of claim 15, further comprising computer executable instructions for identifying the one or more characters using an artificial neural network.

20. The system of claim 15, wherein the memory further comprises an artificial neural network.