MICR-based optical character recognition system and method

• US 7,295,694 B2
• Filed: 02/22/2002
• Issued: 11/13/2007
• Est. Priority Date: 02/22/2002
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Prakash, Ravi, Moon, Rodney G.
• Primary Examiner(s): Johns; Andrew W.
• Assistant Examiner(s): MACKOWEY, ANTHONY M
• Application Number:
  US10/081,417
• Publication Number:
  US 20030161523A1
• Time in Patent Office: 2,090 Days
• Field of Search: 382/139, 382/140, 382/137, 235/379, 705/45
• US Class Current: 382/140
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 30/2253 Recognition of characters printed with magnetic ink G06V30/2247 takes precedence

Abstract

A character recognition system and method. The system comprises an (OCR) optical character reader system for collecting character data by electro-optically scanning printed characters; a conversion system for converting the character data to a Magnetic Ink Character Recognition (MICR) format; and a recognition engine for interpreting the converted character data using a MICR algorithm.

Claims

1. A character recognition system, comprising:

an optical character reader system for collecting character data by electro-optically scanning printed characters;

a conversion system for converting the character data to a Magnetic Ink Character Recognition (MICR) format from a non-MICR format; and

a recognition engine for interpreting the converted character data using a MICR algorithm;

wherein the conversion system scales the character data to a pel density associated with digitalized data obtained by a character recognition device using a multigap MICR read head.

2. The character recognition system of claim 1, wherein the optical character reader system scans at a pel density in a range of approximately 200 to 600 dpi.

3. The character recognition system of claim 1, wherein the character data is stored in a grey scale image format.

4. The character recognition system of claim 3, wherein the conversion system converts the grey scale image format to a black and white image format.

5. The character recognition system of claim 1, wherein the conversion system scales the character data to approximately 0.33 millimeters/pixel in a horizontal dimension and 0.43 millimeters/pixel in a vertical dimension.

6. The character recognition system of claim 1, wherein the printed characters are printed in an E13B font.

7. A method for performing character recognition, comprising:

collecting character data by electro-optically scanning printed characters;

converting the character data to a Magnetic Ink Character Recognition (MICR) format from a non-MICR format; and

interpreting the converted character data using a MICR algorithm;

wherein the converting step scales the character data to a pel density associated with digitalized data obtained by a character recognition device using a multigap MICR read head.

8. The method of claim 7, wherein the character data is scanned at a pel density in a range of approximately 200 to 600 dpi.

9. The method of claim 7, wherein the collection step stores the character data in a grey scale image format.

10. The method of claim 9, wherein the converting step converts the grey scale image format to a black and white image format.

11. The method of claim 7, wherein the converting step scales the character data to approximately 0.33 millimeters/pixel in a horizontal dimension and 0.43 millimeters/pixel in a vertical dimension.

12. The method of claim 7, wherein the printed characters are printed in an E13B font.

13. A program product stored on a computer readable medium for performing character recognition, comprising:

means for accessing character data collected by an electro-optical scanning system;

means for converting the character data to a spatial resolution and density as if captured by a Magnetic Ink Character Recognition (MICR) read head; and

means for interpreting the converted character data using a MICR algorithm;

wherein the converting means scales the character data to a pel density associated with digitalized data obtained by a character recognition device using a multigap MICR read head.

14. The program product of claim 13, wherein the character data comprises a pel density in a range of approximately 200 to 600 dpi.

15. The program product of claim 13, wherein the converting means scales the character data to approximately 0.33 millimeters/pixel in a horizontal dimension and 0.43 millimeters/pixel in a vertical dimension.

16. The program product of claim 13, wherein the converting means converts a grey scale image format to a black and white image format.

17. The program product of claim 13, wherein the character data collected by the electro-optical scanning system comprises characters printed in an E13B font.

18. A multi-voting character recognition engine for analyzing an inputted set of printed characters, comprising:

a plurality of character recognition systems, wherein each character recognition system independently analyzes the inputted set of printed characters, and wherein one of the character recognition systems includes;

an optical character reader system for collecting character data by electro-optically scanning printed characters;

a conversion system for converting the character data to a Magnetic Ink Character Recognition (MICR) format;

a recognition engine for interpreting the converted character data using a MICR algorithm; and

a voting system for combining results from each of the plurality of character recognition systems and determining a recognized set of characters;

wherein the conversion system scales the character data to a pel density associated with digitalized data obtained by a character recognition device using a multigap MICR read head.

19. The multi-voting character recognition engine of claim 18, wherein the inputted set of printed characters are printed in an E13B font.