MULTI-COLOR DROPOUT FOR SCANNED DOCUMENT

• US 20080205751A1
• Filed: 02/26/2007
• Published: 08/28/2008
• Est. Priority Date: 02/26/2007
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Mischler, Gregory S.
• Granted Patent: US 7,853,074 B2
• Time in Patent Office: Days
• US Class Current: 382/163
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: H04N 1/38 Circuits or arrangements for blanking or otherwise eliminating unwanted parts of pictures H04N1/387 takes precedence

Abstract

A method for removing unwanted form color content from a scanned document by segmenting the image into two or more tiles (14). Each tile (14) is classified into at least a first and second set according to its combination of background and color content. A background color is identified from the first set of tiles (14). At least one form color is identified from the second set of tiles. A transform is applied that shifts form color image data values toward background color data values.

Claims

1. A method for removing at least one unwanted form color content from scanned image data for a document, the method comprising:

a) obtaining the scanned document image data in a color data format;

b) segmenting the image data into two or more tiles;

c) classifying each tile into at least first and second sets according to its combination of background and color content;

d) identifying a background color from the first set of tiles;

e) identifying at least one form color from the second set of tiles; and

f) applying a transform that shifts form color image data values toward background color values.

2. The method of claim 1 wherein classifying each tile comprises forming red, green, and blue histograms for each tile.

3. The method of claim 1 wherein classifying each tile comprises the step of reducing the resolution of the tile.

4. The method of claim 1 wherein the color format is red, green, blue (RGB) format.

5. The method of claim 1 wherein the tiles are substantially non-overlapping.

6. The method of claim 1 wherein applying a transform comprises applying coefficients that shift form color values toward background color values.

7. The method of claim 1 wherein identifying the background color comprises:

a) transforming RGB color data to HSV color data; and

b) identifying the most common hue color data value for pixels having a hue color data value within about +/−

10 degrees of the background color.

8. The method of claim 1 further comprising reducing the resolution of the image data.

9. The method of claim 1 wherein identifying at least one form color comprises:

a) transforming RGB color data to HSV (hue, saturation, value) color data; and

b) finding the most common hue color data value.

10. A method for removing unwanted form color content from scanned image data for a document, the method comprising:

a) obtaining the scanned document image data in a color data format;

b) segmenting the image data into two or more tiles;

c) characterizing each tile by its color content with the steps of;

(i) generating a red histogram for red color values within the tile;

(ii) generating a green histogram for green color values within the tile;

(iii) generating a blue histogram for blue color values within the tile;

(iv) determining, according to the red, green, and blue histogram distributions, whether the tile contains predominantly neutral background content, or predominantly form color content, or a combination of background and color content;

d) identifying a background color according to tiles having predominantly neutral background content;

e) identifying at least one form color according to tiles having predominantly form color content; and

f) selectively transforming pixels having the at least one form color toward the background color.

11. The method of claim 10 wherein selectively transforming comprises applying coefficients that shift form color values toward background color values.

12. The method of claim 10 wherein identifying the background color comprises:

a) transforming RGB color data to HSV color data; and

b) finding the most common hue color data value for pixels having a hue color data value within about +/−

10 degrees of the background color.

13. The method of claim 10 wherein determining, according to the red, green, and blue histogram distributions, whether the tile contains predominantly neutral background content, or predominantly form color content, or a combination of background and color content comprises identifying one or more peak values in the red, green, or blue histogram distributions.

14. The method of claim 10 wherein identifying at least one form color comprises converting an RGB coordinate value to an HSV coordinate value.

15. The method of claim 10 wherein characterizing each tile further comprises reducing the resolution of the image data within the tile.

16. The method of claim 10 wherein the color format is red, green, blue (RGB) format.

17. The method of claim 10 wherein the tiles are substantially non-overlapping.

18. The method of claim 10 wherein the same steps are executed for processing each document in a succession of documents.

19. The method of claim 10 wherein selectively transforming pixels comprises generating transform coefficients based on maximum and minimum RGB data values from the identified form color and applying the transform coefficients to each pixel'"'"'s maximum and minimum RGB data values.

20. A method for scanning documents comprising:

a) scanning a first document containing a first form color and a first background color;

b) detecting at least the first form color and the first background color from the scanned data for the first document;

c) calculating and applying a first transform according to the detected first form color and first background color, wherein the first transform shifts the first form color toward the first background color;

d) scanning a second document containing a second form color and a second background color, wherein the second form color differs from the first form color and the second background color differs from the first background color;

e) detecting at least the second form color and the second background color from the scanned data for the second document; and

f) calculating and applying a second transform according to the detected second form color and second background color, wherein the second transform shifts the second form color toward the second background color.

21. The method of claim 20 wherein detecting at least the first form color and first background color comprises segmenting the document into a plurality of tiles and generating a red, green, and blue histogram for each tile.

22. A method for removing at least one unwanted form color from scanned document data comprising:

a) forming a plurality of non-overlapping segments of the document data;

b) generating a red, a green, and a blue histogram for each segment;

c) detecting one or more peaks in any of the red, green, or blue histograms;

d) detecting a background color according to the peaks;

e) transforming peak values from the red, green, and blue histograms to hue, saturation, and value coordinate values;

f) analyzing the hue, saturation, and value coordinate values; and

g) detecting the at least one unwanted form color according to the hue, saturation, and value coordinate values.

23. A method for scanning a plurality of documents, wherein providing document data for each document in the plurality of documents repeats the steps of:

a) obtaining the scanned document image data in a color data format;

b) calculating a background color and at least one form color according to the scanned document image data; and

c) calculating and applying a transform according to the at least one form color and background color, wherein the transform shifts the form color toward the background color.

24. A method for scanning documents comprising:

a) scanning a document containing at least first and second form colors and a background color;

b) detecting the first form color and the background color from the scanned document data;

c) calculating and applying a first transform according to the detected first form color and background color, wherein the first transform shifts the first form color toward the background color;

d) detecting the second form color from the scanned document data; and

e) calculating and applying a second transform according to the detected second form color and background color, wherein the second transform shifts the second form color toward the background color.

25. The method of claim 24 further comprising applying the first and second transforms to the scanned document data.