Image segmentation using blur and color

1. A method comprising:

grouping, by at least one processor, at least some pixels of an image together to form a plurality of super-pixels;

segmenting, by the at least one processor, the image into different segments, where the segmenting is based at least partially upon an estimate of blur of respective ones of the super-pixels, where at least two of the segments each comprise a plurality of the super-pixels;

changing, by the at least one processor, the segmenting of two or more of the segments based, at least partially, upon color in the image, and

calculating, by the at least one processor, color probability of the super-pixels, where the calculation of the color probability is used for the changing of the segmenting.

2. A method as in claim 1 where the estimate of blur for a respective one of the super-pixels comprises one or more of:

a maximum pixel blur of all pixels inside the super-pixel,

a sum of the blur of all the pixels inside the super-pixel,

a mean of the blur of all the pixels inside the super-pixel.

3. A method as in claim 1 where the segmenting comprises applying thresholding to a first segmentation to produce a second segmentation.

4. A method as in claim 3 where the thresholding comprises use of alpha-expansion algorithm, where data cost is defined as how a blur measure of the respective super-pixels compares against the selected adaptive threshold (T).

5. A method as in claim 1 where the segmenting and/or the changing comprises use of user input from a user.

6. A method as in claim 1 where the changing, based upon color, comprises use of a graph cut algorithm to the different segments.

7. A method comprising:

segmenting, by at least one processor, an image into different segments, where the segmenting is based at least partially upon an estimate of blur of areas of the image; and

changing, by the at least one processor, the segmenting of two or more of the segments based, at least partially, upon color in the image,

where the segmenting forms a map comprising at least a first blur layer of the areas based upon the estimate of blur and a different second blur layer of the areas based upon the estimate of blur, and the method further comprises using shrinking along one or more boundaries between the first and second layers on the map.

8. An apparatus comprising

at least one processor; and

at least one non-transitory memory including computer program code, the at least one memory and the computer program code configured, with the at least one processor, cause the apparatus at least to:

group at least some pixels of an image together to form a plurality of super-pixels;

segment the image into different segments, where segmenting of the image into different segments is based at least partially upon an estimate of blur of respective ones of the super-pixels, where at least two of the segments each comprise a plurality of the super-pixels;

change the segmenting of two or more of the segments based, at least partially, upon color in the image; and

calculate color probability of the super-pixels, where the calculation of the color probability is used for the changing of the segmenting.

9. An apparatus as claimed in claim 8 where the estimate of blur for a respective one of the super-pixels comprises one or more of:

a maximum pixel blur of all pixels inside the super-pixel,

a sum of the blur of all the pixels inside the super-pixel,

a mean of the blur of all the pixels inside the super-pixel.

10. An apparatus as claimed in claim 8 where the segment of the image comprises applying thresholding to a first segmentation to produce a second segmentation.

11. An apparatus as claimed in claim 10 where the at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to use of alpha-expansion algorithm for the thresholding, where data cost is defined as how a blur measure of the respective super-pixels compares against the selected adaptive threshold (T).

12. An apparatus as claimed in claim 8 where the segment of the image and/or the change of the segment of the image comprises use of user input from a user.

13. An apparatus as claimed in claim 8 where the change of the segment of the image, based upon color, comprises the at least one memory and the computer program code being configured, with the at least one processor, to use of a graph cut algorithm to the different segments.

14. An apparatus as claimed in claim 8 further comprising:

at least one printed wiring board having the at least one memory and the at least one processor thereon;

an electrical display connected to the at least one printed wiring board;

a receiver connected to the at least one printed wiring board;

a transmitter connected to the at least one printed wiring board; and

a battery connected to the at least one printed wiring board.

15. An apparatus comprising:

at least one processor; and

at least one non-transitory memory including computer program code, the at least one memory and the computer program code configured, with the at least one processor, cause the apparatus at least to:

segment an image into different segments, where segmenting of the image into different segments is based at least partially upon an estimate of blur of areas of the image; and

change the segmenting of two or more of the segments based, at least partially, upon color in the image,

where the segment of the image forms a map comprising at least a first blur layer of the areas based upon the estimate of blur and a different second blur layer of the areas based upon the estimate of blur, and the method further comprises using shrinking along one or more boundaries between the first and second layers on the map.

16. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising:

grouping at least some pixels of an image together to form a plurality of super pixels;

segmenting the image into different segments, where the segmenting is based at least partially upon an estimate of blur of respective ones of the super-pixels, where at least two of the segments each comprise a plurality of the super-pixels;

changing the segmenting of two or more of the segments based, at least partially, upon color in the image; and

calculating color probability of the super-pixels, where the calculation of the color probability is used for the changing of the segmenting.