Group average filter algorithm for digital image processing

• US 20060193530A1
• Filed: 04/24/2006
• Published: 08/31/2006
• Est. Priority Date: 08/11/2003
• Status: Active Grant

• Current Assignee: Scanbuy Incorporated
• Original Assignee: Scanbuy Incorporated
• Inventors: Zastepine, Roman, Shrivastava, Prateek, Attia, Olivier, Outmezguine, Avi
• Granted Patent: US 7,245,780 B2
• Time in Patent Office: Days
• US Class Current: 382/254
• CPC Class Codes: G06K 7/10851 Circuits for pulse shaping, amplifying, eliminating noise signals, checking the function of the sensing device basic electronic circuitry H03
• CPC Class Codes: G06K 7/14 using light without selection of wavelength, e.g. sensing reflected white light G06K7/10831 - G06K7/1097 take precedence
• CPC Class Codes: G06T 2207/20192 Edge enhancement; Edge preservation
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening

Abstract

This present invention discloses a system and method for enhancing images of barcodes and other similar objects taken by the digital camera connected to or embedded in a mobile device. This filter works by converting the image into its equivalent gray scale. The algorithm then computes the mean pixel intensity value of a row of pixels in the image. The row is divided into sections and the mean pixel intensity of each section is also calculated. The pixels in each section are processed according to the relation of the relative mean intensities of the row and the section. Once each pixel has been processed, the image is reassembled from its divided sections.

Claims

1-7. -7. (canceled)

8. A method for processing digital images, comprising:

converting an image to a two-dimensional array, wherein the two-dimensional array comprises one or more rows of pixels, and wherein each row of pixels comprises one or more row sections;

computing a mean intensity of a row of pixels;

computing a mean intensity of a row section of the row of pixels;

if the mean intensity of the row section is greater than the mean intensity of the row of pixels, processing the pixels in the row section according to a first method;

if the mean intensity of the row section is less than the mean intensity of the row of pixels, processing the pixels in the row section according to a second method; and

wherein each of the first method and the second method comprises comparing the mean intensity of the row of pixels to a value computed as a function of a non-zero percentage threshold and an intensity of a pixel in the row section.

9. The method of claim 8, wherein for the first method the computed value is the sum of the intensity of the pixel in the row section and the product of the non-zero percentage threshold and the intensity of the pixel in the row section.

10. The method of claim 9, wherein the first method further comprises:

assigning the pixel in the row section an intensity corresponding to white if the computed value is greater than the mean intensity of the row; and

assigning the pixel in the row section an intensity corresponding to black if the computed value is less than the mean intensity of the row.

11. The method of claim 8, wherein for the second method the computed value is the product of the non-zero percentage threshold and the intensity of the pixel in the row section subtracted from the intensity of the pixel in the row section.

12. The method of claim 11, wherein the second method further comprises:

assigning the pixel in the row section an intensity corresponding to white if the computed value is greater than the mean intensity of the row; and

assigning the pixel in the row section an intensity corresponding to black if the computed value is less than the mean intensity of the row.

13. The method of claim 8, further comprising:

if the mean intensity of the row section is equal to the mean intensity of the row, disregarding the pixels in the row section.

14. The method of claim 8, further comprising:

mapping each pixel of the two-dimensional array to a corresponding grayscale equivalent.

15. The method of claim 8, further comprising:

prior to processing the pixels in the two-dimensional array, mapping each pixel of the two-dimensional array to a corresponding grayscale equivalent.

16. The method of claim 8, further comprising:

processing the pixels in each row section of the row of pixels; and

reassembling the row of pixels after the one or more row sections have been processed.

17. The method of claim 8, further comprising:

processing the pixels in each row of pixels of the two-dimensional array; and

reassembling the rows of pixels after the one or more rows have been processed.

18. The method of claim 8, wherein the number of row sections is in the range of three row sections to ten row sections.

19. The method of claim 8, wherein the number of row sections is a number received from a user.

20. The method of claim 8, wherein the number of row sections is a predetermined number of row sections.

21. The method of claim 8, wherein the number of row sections is the same for each row of pixels.

22. The method of claim 8, wherein the non-zero percentage threshold is less than or equal to twenty.

23. The method of claim 8, wherein the image is a barcode image.

24. The method of claim 23, further comprising:

processing the pixels in each row of pixels of the two-dimensional array;

reassembling the rows of pixels after the one or more rows have been processed; and

decoding the barcode image.

25. The method of claim 23, further comprising:

capturing the barcode image using a camera-enabled mobile device.

26. A computer readable medium storing computer executable instructions for processing digital images, the executable instructions comprising:

converting an image to a two-dimensional array, wherein the two-dimensional array comprises one or more rows of pixels, and wherein each row of pixels comprises one or more row sections;

computing a mean intensity of a row of pixels;

computing a mean intensity of a row section of the row of pixels;

if the mean intensity of the row section is greater than the mean intensity of the row of pixels, processing the pixels in the row section according to a first method;

if the mean intensity of the row section is less than the mean intensity of the row of pixels, processing the pixels in the row section according to a second method; and

wherein each of the first method and the second method comprises comparing the mean intensity of the row of pixels to a value computed as a function of a non-zero percentage threshold and an intensity of a pixel in the row section.

27. A device for processing digital images, comprising:

a processor executing an application that is configured to;

convert an image to a two-dimensional array, wherein the two-dimensional array comprises one or more rows of pixels, and wherein each row of pixels comprises one or more row sections;

compute a mean intensity of a row of pixels;

compute a mean intensity of a row section of the row of pixels;

if the mean intensity of the row section is greater than the mean intensity of the row of pixels, process the pixels in the row section according to a first method;

if the mean intensity of the row section is less than the mean intensity of the row of pixels, process the pixels in the row section according to a second method; and

wherein each of the first method and the second method comprises comparing the mean intensity of the row of pixels to a value computed as a function of a non-zero percentage threshold and an intensity of a pixel in the row section.

28. The device of claim 27, wherein the image is a barcode image, the device further comprising:

a digital camera that is configured to capture the barcode image.