Gray scale image cleaning system and method

• US 20070041629A1
• Filed: 08/18/2005
• Published: 02/22/2007
• Est. Priority Date: 08/18/2005
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Sathe, Madhura, Prakash, Ravinder, Moon, Rodney, Kruppa, Robert
• Granted Patent: US 7,492,974 B2
• Time in Patent Office: Days
• US Class Current: 382/139
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal

Abstract

A gray scale image cleaning algorithm for improved check code line OCR. An image processing system for processing a gray scale image is provided that includes: a system for generating a first thresholded black white image from the gray scale image; a system for generating a second thresholded black white image from the gray scale image, wherein the second thresholded black white image is generated with a higher threshold value than the first thresholded black white image; and a system for logically combining the first and second thresholded black white images to generate a composite image.

Claims

1. An image processing system for processing a gray scale image, comprising:

a system for generating a first thresholded black white image from the gray scale image;

a system for generating a second thresholded black white image from the gray scale image, wherein the second thresholded black white image is generated with a higher threshold value than the first thresholded black white image; and

a system for logically combining the first and second thresholded black white images to generate a composite image.

2. The image processing system of claim 1, wherein the gray scale image comprises a check image having a code line.

3. The image processing system of claim 2, further comprising a code line optical character recognition (OCR) system that applies a set of magnetic ink character recognition (MICR) rules to identify and capture the code line from the check image.

4. The image processing system of claim 3, wherein the code line OCR system further performs an OCR process on the code line to generate a set of code line data.

5. The image processing system of claim 4, further comprising a recursive thresholding system that generates a set of composite images by altering a threshold value associated with at least one of the first and second thresholded black white images.

6. The image processing system of claim 5, wherein the recursive thresholding system includes a voting system that examines multiple sets of code line data.

7. The image processing system of claim 1, wherein:

the first thresholded black white image comprises a normally thresholded black white image;

the second thresholded black white image comprises a skeleton image; and

the system for logically combining the images causes black pixel regions in the skeleton image to grow based on pixel information in the normally thresholded black white image.

8. The image processing system of claim 7, wherein the composite image is generated by:

identifying each pixel location in the skeleton image that comprises a black pixel;

for each pixel location identified in the skeleton image, examining an associated pixel location in the normally thresholded black white image to identify each neighbor of the associated pixel location; and

generating the composite image to include each identified black pixel from the skeleton image and any black neighboring pixels identified from the normally thresholded black white image.

9. The image processing system of claim 1, further comprising a connected component cleaning system that eliminates connected components in the composite image having fewer than N black pixels, where N is a predetermined integer.

10. A program product stored on a computer readable medium for processing a code line in a gray scale image, comprising:

program code configured for generating a normally thresholded black white image from the gray scale image;

program code configured for generating a skeleton image from the gray scale image, wherein the skeleton image comprises an altered threshold setting; and

program code configured for logically combining the normally thresholded black white image and the skeleton image to generate a composite image.

11. The program product of claim 10, wherein the program code configured for logically combining the normally thresholded black white image and the skeleton image comprises program code configured for:

identifying each pixel location in the skeleton image that comprises a black pixel;

for each pixel location identified in the skeleton image, examining an associated pixel location in the normally thresholded black white image to identify each neighbor of the associated pixel location; and

generating the composite image to include each identified black pixel from the skeleton image and any black neighboring pixels identified from the normally thresholded black white image.

12. The program product of claim 10, further comprising program code configured for eliminating connected components in the composite image having fewer than N black pixels, where N is a predetermined integer.

13. The program product of claim 12, further comprising program code configured for applying a set of magnetic ink character recognition (MICR) rules to identify and capture the code line from the check image.

14. The program product of claim 13, further comprising program code configured for performing an OCR process on the code line to generate a set of code line data.

15. The program product of claim 14, further comprising program code configured for generating a set of composite images by altering a threshold value associated with at least one of the normally thresholded black white image and the skeleton image.

16. The program product of claim 15, further comprising program code configured for examining multiple sets of code line data.

17. A method of processing a code line in a gray scale image, comprising:

generating a normally thresholded black white image from the gray scale image;

generating a skeleton image from the gray scale image, wherein the skeleton image comprises an altered threshold setting; and

logically combining the normally thresholded black white image and the skeleton image to generate a composite image.

18. The method of claim 17, wherein the step of logically combining the normally thresholded black white image and the skeleton image comprises:

identifying each pixel location in the skeleton image that comprises a black pixel;

for each pixel location identified in the skeleton image, examining an associated pixel location in the normally thresholded black white image to identify each neighbor of the associated pixel location; and

generating the composite image to include each identified black pixel from the skeleton image and any black neighboring pixels identified from the normally thresholded black white image.

19. The method of claim 17, further comprising the step of eliminating connected components in the composite image having fewer than N black pixels, where N is a predetermined integer.

20. The method of claim 19, further comprising the step of applying a set of magnetic ink character recognition (MICR) rules to identify and capture the code line from the check image.

21. The method of claim 20, further comprising the step of performing an OCR process on the code line to generate a set of code line data.

22. The method of claim 21, further comprising the step of generating a set of composite images by altering a threshold value associated with at least one of the normally thresholded black white image and the skeleton image.

23. The method of claim 22, further comprising the step of examining multiple sets of code line data.

24. A method for deploying an image processing system, comprising:

providing a computer infrastructure being operable to;

generate a normally thresholded black white image from a gray scale image;

generate a skeleton image from the gray scale image; and

logically combine the normally thresholded black white image and the skeleton image to generate a composite image.

25. Computer software embodied in a propagated signal for implementing an image processing system, the computer software comprising instructions to cause a computer to perform the following functions:

generate a normally thresholded black white image from the gray scale image;

generate a skeleton image from the gray scale image; and

logically combine the normally thresholded black white image and the skeleton image to generate a composite image.