Image processing

• US 10,248,825 B2
• Filed: 08/29/2014
• Issued: 04/02/2019
• Est. Priority Date: 08/29/2014
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Forman, George
• Primary Examiner(s): Liew, Alex Kok S
• Application Number:
  US15/506,118
• Publication Number:
  US 20170286738A1
• Time in Patent Office: 1,677 Days
• CPC Class Codes: G06K 7/1478 adapting the threshold for pixels in a CMOS or CCD pixel sensor for black and white recognition
• CPC Class Codes: G06V 30/1478 of characters or characters lines

Abstract

An example method is of image processing provided in according with one implementation of the present disclosure. The method includes receiving an image, placing a window across the image, and computing a set of all occurring grayscale values within the window. The method further includes computing a threshold value based on the set of all occurring grayscale values within the window and determining an output pixel value of at least one pixel from the window based on the threshold value.

Claims

1. A method of image processing comprising, by at least one processing device:

receiving an image;

placing a window across the image;

computing a set of all occurring grayscale values within the window;

computing a threshold value based on the set of all occurring unique grayscale values within the window, including considering every occurring unique grayscale value without considering a number of occurrences of each occurring unique grayscale value within the set; and

determining an output pixel value of at least one pixel from the window based on the threshold value.

2. The method of claim 1, wherein computing the set of all occurring grayscale values within the window further comprises:

computing a histogram of grayscale values for the window; and

selecting the grayscale values that have a non-zero count to define the set of all occurring grayscale values.

3. The method of claim 1, wherein computing the threshold value further includes computing an average grayscale value of the set of all occurring grayscale values in the window.

4. The method of claim 1, wherein computing the threshold value further includes computing a median grayscale value of the set of all occurring grayscale values in the window.

5. The method of claim 1, wherein the at least one pixel is a middle pixel of the window, and wherein the image includes a barcode.

6. The method of claim 1, wherein the output pixel value of the at least one pixel is identified as white if a grayscale value of the at least one pixel is above the threshold value, and wherein the output pixel value of the at least one pixel is identified as black if a grayscale value of the at least one pixel is below the threshold value.

7. The method of claim 2, wherein sliding the window across the image further comprises:

removing and adding at least one pixel from the window during each sliding iteration, and using the histogram to keep track of the number of pixels at each grayscale value in the window.

16. The method of claim 1, wherein computing the threshold value comprises computing an average of the set of all occurring unique grayscale values.

8. A system comprising:

at least one processing device with a control unit to;

process an image;

move a window across the image;

compute a histogram of grayscale values for the window; and

compute a set of all occurring grayscale values within the window by selecting the grayscale values that have a non-zero count;

compute a threshold value based on the set of all occurring unique grayscale values within the window, including considering every occurring unique grayscale value without considering a number of occurrences of each occurring unique grayscale value within the set; and

determine an output pixel value of at least one pixel from the window based on the threshold value.

9. The system of claim 8, the control unit further to:

compute an average grayscale value of the set of all occurring grayscale values in the window to compute the threshold value.

10. The system of claim 8, wherein the at least one pixel is a middle pixel of the widow, and wherein the image is an optical character recognition image.

11. The system of claim 8, wherein the output pixel value of the at least one pixel is identified as white if a grayscale value of the at least one pixel is above the threshold value, and wherein the output pixel value of the at least one pixel is identified as black if a grayscale value of the at least one pixel is below the threshold value.

12. The system of claim 8, the control unit further to:

remove and add at least one pixel from the window during each sliding iteration, and use the histogram to keep track of the number of pixels at each grayscale value in the window.

13. A non-transitory machine-readable storage medium encoded with instructions executable by at least one processor, the machine-readable storage medium comprising instructions to:

process an image;

iteratively slide a window across the image;

compute a histogram of grayscale values for the window; and

compute a set including all occurring grayscale values within the window by including grayscale values having a non-zero count in the histogram;

compute a threshold value based on the set of all occurring unique grayscale values within the window, including considering every occurring unique grayscale value without considering a number of occurrences of each occurring unique grayscale value within the set; and

identify an output pixel value of at least one pixel from the window based on the threshold value.

14. The non-transitory machine-readable storage medium, further comprising instructions to:

compute an average grayscale value of the set of all occurring grayscale values in the window to compute the threshold value.

15. The non-transitory machine-readable storage medium, further comprising instructions to:

identify the output pixel value of the at least one pixel as white if a grayscale value of the at least one pixel is above the threshold value, and identify the output pixel value of the at least one pixel as black if a grayscale value of the at least one pixel is below the threshold value.