METHOD OF SELECTING ONE OF A PLURALITY OF BINARIZATION PROGRAMS

• US 20010043748A1
• Filed: 12/19/1997
• Published: 11/22/2001
• Est. Priority Date: 12/19/1997
• Status: Active Grant

• Current Assignee: NCR Atleos Corp.
• Original Assignee: NCR Corporation (NCR Voyix Corporation)
• Inventors: WESOLKOWSKI, SLAWOMIR B., HASSANEIN, KHALED S.
• Granted Patent: US 6,411,737 B2
• Time in Patent Office: Days
• US Class Current: 382/237
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone

Abstract

A document processing apparatus comprises a scanner for scanning a bank check to obtain gray scale image data associated with the bank check. A processor is provided for (i) selecting one of a plurality of binarization programs based upon the gray scale image data, and (ii) applying the binarization program selected to at least a portion of the gray scale image data to provide a binary image of at least a portion of the bank check.

Claims

1. A document processing apparatus comprising:

a scanner for scanning a bank check to obtain gray scale image data associated with the bank check; and

a processor for (i) selecting one of a plurality of binarization programs based upon the gray scale image data, and (ii) applying the binarization program selected to at least a portion of the gray scale image data to provide a binary image of at least a portion of the bank check.

2. A document processing apparatus according to

claim 1

, wherein the processor includes a neural network which is applied to at least one value which has been calculated based upon the gray scale image data.

3. A document processing apparatus according to

claim 2

, wherein the neural network accepts as input a value indicative of average intensity of pixels associated with the check.

4. A document processing apparatus according to

claim 2

, wherein the neural network accepts as input a value indicative of standard deviation of pixels associated with the check.

5. A document processing apparatus according to

claim 2

, wherein the neural network accepts as input a value indicative of histogram type of pixels associated with the check.

6. A method of processing a bank check, the method comprising the steps of:

(a) scanning the bank check to obtain gray scale image data associated with the bank check;

(b) selecting one of a plurality of binarization programs based upon the gray scale image data obtained in step (a);

(c) applying the binarization program selected in step (b) to at least a portion of the gray scale image data obtained in step (a) to provide a binary image of at least a portion of the bank check.

7. A method according to

claim 6

, wherein step (b) includes the step of:

(b-1) applying a neural network to at least one value which has been calculated based upon the gray scale image data obtained in step (a).

8. A method according to

claim 7

, wherein step (b-1) includes the step of:

(b-1-1) accepting as input a value indicative of an average intensity of pixels associated with the check.

9. A method according to

claim 7

, wherein step (b-1) includes the step of:

(b-1-1) accepting as input a value indicative of standard deviation of intensity of pixels associated with the check.

10. A method according to

claim 7

, wherein step (b-1) includes the step of:

(b-1-1) accepting as input a value indicative of histogram type of pixels associated with the check.