Image enhancement method and apparatus

• US 8,059,892 B1
• Filed: 10/01/2008
• Issued: 11/15/2011
• Est. Priority Date: 10/01/2008
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Fan, Jian
• Primary Examiner(s): Sherali; Ishrat I
• Application Number:
  US12/243,793
• Time in Patent Office: 1,140 Days
• Field of Search: 382162-167, 382/173, 382274-275, 382/254, 358/1.2, 358/1.9, 358 326- 327, 358515-523, 348/223.1
• US Class Current: 382/167
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/20152 Watershed segmentation
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

An image enhancement method includes segmenting pixels of an image into background pixels and non-background pixels and computing a color scaling factor based on the color of the background pixels compared to white. The color scaling factor is then applied to the background pixels and the non-background pixels.

Claims

1. A method performed by at least one processor of a computer system, the method comprising:

segmenting, using a processor, pixels of an image into background pixels and non-background pixels;

computing, using a processor, a color scaling factor based on the color of the background pixels compared to white; and

applying, using a processor, the color scaling factor to the background pixels and the non-background pixels.

2. The method of claim 1, wherein computing the color scaling factor includes computing a color scaling factor for each pixel in the image.

3. The method of claim 1, wherein segmenting the pixels comprises:

determining gradient magnitude values at respective pixels of the image;

thresholding the gradient magnitude values with a global threshold to produce thresholded gradient magnitude values;

segmenting the pixels into respective regions in accordance with a watershed transform of the thresholded magnitude values; and

generating a classification record labeling each pixel as background pixels or non-background pixels.

4. The method of claim 3, wherein pixels are labeled as background pixels or non-background pixels in response to the size of the region containing the pixels.

5. The method of claim 3, wherein pixels are labeled as background pixels or non-background pixels in response to the luminance of the region containing the pixels.

6. The method of claim 3, wherein pixels are labeled as background pixels or non-background pixels in response to the distance between the color of the pixels in the region containing the pixels and a reference color.

7. The method of claim 3, wherein thresholding the gradient magnitude computing a histogram of the gradient magnitude.

8. The method of claim 1, wherein an sRGB colorspace is associated with the image, and further comprising converting the sRGB image to linear RGB.

9. The method of claim 1, wherein segmenting the pixels comprises segmenting the pixels of a plurality of images.

10. The method of claim 9, further comprising computing the color of the background pixels of selected ones of the plurality of images, and wherein computing the color scaling factor includes comparing the color of the background pixels to white.

11. The method of claim 10, wherein the plurality of images is a sample of images from a set of images, the method further comprising enhancing the set of images.

12. The method of claim 10, wherein applying the color scaling factor to the background pixels and the non-background pixels includes applying the color scaling factor to the pixels of the set of images, and further comprising:

if a given image of the set of images meets a first condition, applying a first enhancement to the given image; and

if the given image does not meet the first condition, applying a second enhancement to the given image.

13. The method of claim 12, further comprising segmenting pixels of the given image into background pixels and non-background pixels based on the color of the background pixels of the selected ones of the sample images.

14. A non-transitory computer readable storage medium storing instructions that when executed cause a processor to perform a method comprising:

segmenting pixels of an image into background pixels and non-background pixels computing a color scaling factor based on the color of the background pixels compared to white; and

applying the color scaling factor to the background pixels and the non-background pixels.

15. The computer readable storage medium of claim 14, wherein computing the color scaling factor includes computing a color scaling factor for each pixel in the image.

16. The computer readable storage medium of claim 14, wherein segmenting the pixels comprises segmenting the pixels of a plurality of images.

17. The computer readable storage medium of claim 16, further comprising computing the color of the background pixels of selected ones of the plurality of images, and wherein computing the color scaling factor includes comparing the color of the background pixels to white.

18. An apparatus, comprising:

a memory for storing computer executable instructions; and

a processing unit for accessing the memory and executing the computer executable instructions, the computer executable instructions comprising;

a segmentation module operable to segment pixels of an image into background pixels and non-background pixels; and

a color correction module operable to compute a color scaling factor based on the color of the background pixels compared to white, and apply the color scaling factor to the background pixels and the non-background pixels.

19. The apparatus of claim 18, wherein computing the color scaling factor includes computing a color scaling factor for each pixel in the image.

20. The apparatus of claim 18, wherein segmenting the pixels comprises segmenting the pixels of a plurality of images.