Methods and systems for segmenting a digital image into regions

• US 8,368,956 B2
• Filed: 12/30/2010
• Issued: 02/05/2013
• Est. Priority Date: 06/15/2006
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Campbell, Richard John, Matsuda, Toyohisa, Chen, Lawrence Shao-hsien
• Primary Examiner(s): TRAN, DUNG D
• Application Number:
  US12/982,718
• Publication Number:
  US 20110096993A1
• Time in Patent Office: 768 Days
• Field of Search: None
• US Class Current: 358/1.9
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20152 Watershed segmentation
• 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 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone

Abstract

Aspects of the present invention relate to methods and systems for segmenting a digital image into regions. A frequency-of-occurrence of image values may be determined excluding a portion of pixels in a digital image. An image value associated with a peak in the frequency-of-occurrence of image values may be identified and associated with an image label. Pixel locations may be labeled based on the associated labels and image values. Additionally, unreliable pixels may be determined and labeled based on the associated labels and image values, and an unreliable pixel may be assigned a label after multiple scan passes of a classification map.

Claims

1. A non-transitory computer-readable medium encoded with a computer program code for a method for labeling an unlabeled pixel in a classification map, said method comprising:

performing a scan pass, of a classification map, in a first direction;

identifying, in said scan pass, an unreliable pixel in said classification map, wherein said unreliable pixel is a pixel, in said classification map, that is not assigned a region identifier associated with a local background image region;

incrementing a scan-direction count for said unreliable pixel if a condition related to a plurality of spatially neighboring pixels to said unreliable pixel is satisfied, wherein said plurality of spatially neighboring pixels includes only pixels previously scanned in said scan pass; and

labeling said unreliable pixel based on said scan-direction count.

2. The method of claim 1, wherein said scan pass of said classification map is one of a plurality of scan passes of said classification map, wherein each scan pass in said plurality of scan passes of said classification map is performed in a different direction.

3. The method of claim 1, wherein said condition is related to the labels of said plurality of spatially neighboring pixels to said unreliable pixel.

4. The method of claim 3, wherein said plurality of neighboring pixels is associated with a four-nearest-neighbor neighborhood in relation to said unreliable pixel.

5. The method of claim 1 further comprising:

performing a second scan pass, of said classification map, in a second direction;

identifying, in said second scan pass, said unreliable pixel in said classification map; and

incrementing said scan-direction count for said unreliable pixel if a second condition related to a second plurality of spatially neighboring pixels to said unreliable pixel is satisfied, wherein said second plurality of spatially neighboring pixels includes only pixels previously scanned in said second scan pass.

6. The method of claim 5, wherein:

said condition is related to the labels of said plurality of spatially neighboring pixels to said unreliable pixel; and

said second condition is related to the labels of said second plurality of spatially neighboring pixels to said unreliable pixel.

7. The method of claim 5, wherein:

said plurality of spatially neighboring pixels is associated with a four-nearest-neighbor neighborhood in relation to said unreliable pixel; and

said second plurality of spatially neighboring pixels is associated with a second four-nearest-neighbor neighborhood in relation to said unreliable pixel.

8. A system for labeling an unlabeled pixel in a classification map, said system comprising:

in a computing system comprising at least one computing device, a classification-map scanner for performing a scan pass, of a classification map, in a first direction;

an unreliable-pixel identifier for identifying, in said scan pass, an unreliable pixel in said classification map, wherein said unreliable pixel is a pixel, in said classification map, that is not assigned a region identifier associated with a local background image region;

an incrementor for incrementing a scan-direction count for said unreliable pixel if a condition related to a plurality of spatially neighboring pixels to said unreliable pixel is satisfied, wherein said plurality of spatially neighboring pixels includes only pixels previously scanned in said scan pass; and

a labeler for labeling said unreliable pixel based on said scan-direction count.

9. The system of claim 8, wherein said scan pass of said classification map is one of a plurality of scan passes of said classification map, wherein each scan pass in said plurality of scan passes of said classification map is performed in a different direction.

10. The system of claim 8, wherein said condition is related to the labels of said plurality of spatially neighboring pixels to said unreliable pixel.

11. The system of claim 10, wherein said plurality of neighboring pixels is associated with a four-nearest-neighbor neighborhood in relation to said unreliable pixel.

12. The system of claim 8 further comprising:

a second classification-map scanner for performing a second scan pass, of said classification map, in a second direction;

a second unreliable-pixel identifier for identifying, in said second scan pass, said unreliable pixel in said classification map; and

wherein said incrementor further increments said scan-direction count for said unreliable pixel if a second condition related to a second plurality of spatially neighboring pixels to said unreliable pixel is satisfied, wherein said second plurality of spatially neighboring pixels includes only pixels previously scanned in said second scan pass.

13. The system of claim 12, wherein:

said condition is related to the labels of said plurality of spatially neighboring pixels to said unreliable pixel; and

said second condition is related to the labels of said second plurality of spatially neighboring pixels to said unreliable pixel.

14. The system of claim 12, wherein:

said plurality of spatially neighboring pixels is associated with a four-nearest-neighbor neighborhood in relation to said unreliable pixel; and

said second plurality of spatially neighboring pixels is associated with a second four-nearest-neighbor neighborhood in relation to said unreliable pixel.