Character recognition

• US 8,391,602 B2
• Filed: 04/08/2010
• Issued: 03/05/2013
• Est. Priority Date: 04/08/2010
• Status: Expired due to Fees

• Current Assignee: University of Calcutta
• Original Assignee: University of Calcutta
• Inventors: Shaikh, Soharab Hossain, Chaki, Nabendu
• Primary Examiner(s): Do, Anh Hong
• Application Number:
  US12/756,612
• Publication Number:
  US 20110249897A1
• Time in Patent Office: 1,062 Days
• Field of Search: 382/173, 382/177, 382/178, 382/179, 382/186, 382/119, 382/228, 382/218, 382/196, 382/138, 382/197, 382/E7.133, 324/452, 324/457, 324/671, 340/5.52, 340/5.82
• 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 non-transitory computer readable medium storing executable instructions that, when executed, cause one or more processors to perform operations 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 computer-readable medium of claim 1, wherein the performing the lateral view 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 computer-readable medium 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 computer-readable medium of claim 2, wherein the horizontal segments have the same height.

5. The computer-readable medium of claim 1, further comprising binarizing the character data.

6. The computer-readable medium of claim 1, further comprising removing noise from the character data.

7. The computer-readable medium of claim 1, further comprising performing oblique/skew detection.

8. The computer-readable medium of claim 1, further comprising segmenting the character data into individual characters, the character data comprising a plurality of characters.

9. The computer-readable medium of claim 1, wherein the contour data is not thinned.

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

11. The computer-readable medium of claim 1, further comprising recognizing cursive characters.

12. The computer-readable medium of claim 1, wherein the operations are substantially font invariant.

13. The computer-readable medium of claim 1, further comprising identifying characters in fonts having variable character widths.

14. The computer-readable medium 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.