Black white image scaling for optical character recognition

• US 7,593,600 B2
• Filed: 03/04/2004
• Issued: 09/22/2009
• Est. Priority Date: 03/04/2004
• Status: Expired due to Fees

• Current Assignee: Toshiba Global Commerce Solutions Holdings Corporation (Toshiba Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Prakash, Ravinder, Thompson, Gerhard Robert
• Primary Examiner(s): Ahmed; Samir A.
• Assistant Examiner(s): Park; Edward
• Application Number:
  US10/793,452
• Publication Number:
  US 20050196071A1
• Time in Patent Office: 2,028 Days
• Field of Search: 382/301, 382/298
• US Class Current: 382/298
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/166 Normalisation of pattern dimensions

Abstract

A system and method for capturing and scaling images includes a scaling engine with the ability to employ a first scaling factor in a first direction and a second scaling factor in a second direction. In addition, the preferred scaling engine manipulates the scaling process so that the scaling calculations are performed using fixed point arithmetic. The preferred scaling engine preserves isolated features such as a single white pixel in a field of black pixels and vice versa. Improved readability is achieved in one embodiment by performing the scaling process multiple times using different degrees of “padding” where padding refers to the technique of surrounding an image with a perimeter of one or more blank (white) pixel elements.

Claims

1. A method for scaling a bi-tonal image, the method comprising:

responsive to receiving a scanned image, determining, by a processor, a first scale factor;

processing, by a processor, a line of the scanned image, wherein the line is oriented parallel to a first axis, and wherein processing comprises;

determining a scanned pixel position of a pixel transition in the line;

dividing the scanned pixel position by the first scale factor to determine a scaled pixel position for the pixel transition; and

responsive to the scaled pixel position for the pixel transition equaling a previous scaled pixel position of a previously processed pixel transition, adjusting the scaled pixel position to prevent the previously processed pixel transition from being overwritten in a scaled image.

2. The method of claim 1, wherein dividing the scanned pixel position includes dividing the scanned pixel position using fixed point arithmetic exclusively.

3. The method of claim 2, wherein dividing the scanned pixel position using fixed point arithmetic exclusively includes:

multiplying each determined scanned pixel location by 10^N, where N is an integer between 2 and 5; and

dividing a result of the multiplication by the first scale factor multiplied by 10^N.

4. The method of claim 2, further, comprising:

determining a second-scale factor, wherein the second scale is different than the first scale factor; and

upon processing the line to obtain an interim scaled image, processing a second line of the interim scaled image, wherein the second line is parallel to a second axis, by;

determining a second scanned pixel position of a second scanned pixel transition in the second line;

dividing the second scanned pixel position by the second scale factor to determine a second scaled pixel position for the second pixel transition; and

responsive to the scaled pixel position for the pixel transition equaling a previous scaled pixel position of a previously processed pixel transition, adjusting the second scaled pixel position to prevent the previously processed pixel transition from being overwritten in the scaled image.

5. The method of claim 4, further comprising:

processing a first image using first x and y scale factors;

scaling a second scanned image using second x and y scale factors, wherein the first x and y scale factors and the second x and y second scale factors differ; and

generating a document containing the first image and the second image.

6. The method of claim 5, wherein generating a document comprises generating a bank statement, and wherein the first scanned image comprises a first check copy and the second scanned image comprises a second check copy.

7. The method of claim 1, further comprising, prior to processing the line, padding the scanned image with a perimeter of empty pixels.

8. The method of claim 7, further comprising:

iterating, a plurality of times, padding the scanned image and processing the line of the scanned image, wherein a number of empty cells in the perimeter varies for each iteration; and

selecting a final scaled image from a set of scaled images produced by iterating.

9. A computer program product comprising computer executable instructions, stored on a computer readable medium, for scaling an image, the computer program product comprising:

instructions for scaling a first scanned image in a first direction using a first scaling factor;

instructions for scaling the first scanned image in a second direction according to a second scaling factor;

wherein at least one image line of a set of image lines in the first scanned image includes an isolated pixel and further wherein the instructions for scaling the first scanned image includes instructions for preserving the isolated pixel in a scaled image;

wherein the instructions for scaling the first scanned image in the first direction includes;

instructions for determining, for each oriented image line oriented in the first direction of the first scanned image, a a scanned pixel position of a pixel transition in each oriented image line; and

instructions for dividing the scanned pixel position by the first scale factor to determine a scaled pixel position for the pixel transition in the scaled image; and

instructions, for adjusting the scaled pixel position to prevent a previously processed pixel transition from being overwritten in the scaled image in response to the scaled pixel position for the pixel transition equaling a previous scaled pixel position of the previously processed pixel transition.

10. The computer program product of claim 9, wherein the instructions for dividing the scanned pixel position include instructions for multiplying the scanned pixel position by 10^N, wherein N is an integer between 2 and 5, and instructions for dividing the resulting product by the first scaling factor multiplied by 10^N.

11. The computer program product of claim 10, wherein the instructions for dividing and the instructions for multiplying include instructions for dividing and multiplying the scanned pixel position value using integer arithmetic exclusively.

12. The computer program product of claim 11, further comprising:

instructions for determining, for second lines oriented in a second direction of the scanned image, a second scanned pixel position of a second scanned pixel transition in the second lines; and

instructions for dividing the second scanned pixel position by the second scale factor to determine a second scaled pixel position for the second pixel transition in the scaled image.

13. The computer program product of claim 12, wherein the instructions for dividing the second scanned pixel position includes instructions for adjusting the scaled pixel position to prevent the previously processed pixel transition from being overwritten in a scaled image in response to the scaled pixel position for the pixel transition equaling a previous scaled pixel position of a previously processed pixel transition.

14. The computer program product of claim 13, further comprising instructions for processing the first scanned image using a first set of first and second scaling factors, and instructions for scaling a second scanned image using a second set of scaling factors to form a second scaled image, wherein the first and second sets of scale factors differ.

15. The computer program product of claim 14, further comprising instructions for generating a document including the scaled image and the second scaled image wherein the document comprises a bank statement, and wherein the first scanned image comprises a first check copy and the second scanned image comprises a second check copy.

16. The computer program product of claim 9 further comprising instructions for padding the first scanned image prior to scaling by appending a perimeter of blank pixels to the first scanned image.

17. The computer program product of claim 16, further comprising:

instructions for iterating, a plurality of times the instructions for padding, the instructions for scaling first scanned image in a first direction, and the instructions for scaling the first scanned image in the second direction, wherein a degree of padding varies during each iteration, wherein a set of scaled images is produced, and

instructions for selecting a single scaled image from among the set of scaled images.

18. An image scaling system, comprising:

a capture device to scan an original image and to produce a bi-tonal image therefrom;

a scaling engine to scale the bi-tonal image using independent x and y scaling factors to produce a scaled image, wherein isolated pixels in the bi-tonal image are preserved in the scaled image;

wherein the scaling engine produces the scaled image using fixed point arithmetic calculations exclusively;

wherein the scaling engine determines a scanned pixel position of a pixel transition in the line;

wherein the scaling engine divides the scanned pixel position by the first scale factor to determine a scaled pixel position for the pixel transition; and

wherein the scaling engine adjusts the scaled pixel position to prevent the previously processed pixel transition from being overwritten in a scaled image in response to the scaled pixel position for the pixel transition equaling a previous scaled pixel position of a previously processed pixel transition.

19. The system of claim 18, wherein the scaling engine pads the bi-tonal image prior to scaling by appending a perimeter of blank pixels around the bi-tonal image.