Method, apparatus and computer program product for compensating eye color defects
View Patent ↗Method, apparatus, and computer program product are provided. The method includes computing a first difference image for a first eye region based on a difference of red pixel intensity and green pixel intensity of each of a first set of pixels associated with the first eye region. The method further includes determining a first eye color defect region by computing a neighborhood processed first difference image by processing the first difference image, computing a first central point of the neighborhood processed first difference image based on a weighted centroid of red pixels associated with the neighborhood processed first difference image, and thereafter computing the first eye color defect region based on the first central point, and the red pixels associated with the first difference image.
1. A method comprising:
computing using a processor a smallest bounding rectangle for enclosing a first eye color defect region;
dividing a neighborhood region of the smallest bounding rectangle into a plurality of regions having an average pixel intensity;
computing an average pixel intensity of the enclosed first eye color defect region, and a number of neighborhood regions having average pixel intensity lesser than a second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region; and
determining presence of an eye color defect at the computed first eye color defect region upon determining the number of neighborhood regions having an average pixel intensity less than the second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region being greater than a second predetermined threshold.
2. The method of claim 1 further comprising:
computing a first difference image for a first eye region based on a difference of red pixel intensity and a green pixel intensity of each of a first set of pixels associated with the first eye region; and
determining the first eye color defect region based on the computing.
3. The method of claim 2 further comprising:
computing a second difference image based on:
difference of a red pixel intensity and a green pixel intensity of a second set of pixels, and
an intensity level of the second set of pixels associated with a second eye region;
determining a second eye color defect region, if the first eye region fails in the verification; and
correcting the eye color defect at the computed second eye color defect region.
4. The method of claims 1 , further comprising performing a verification based on a shape of the first eye color defect region upon verifying presence of the eye color defect at the computed first eye color defect region.
5. The method of claim 1 further comprising correcting the eye color defect at the determined first eye color defect region upon verifying presence of the eye color defect at the determined first eye color defect region.
6. An apparatus comprising:
at least one processor; and
at least one memory comprising data associated with an image and computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
compute a smallest bounding rectangle for enclosing a first eye color defect region;
divide a neighborhood region of the smallest bounding rectangle into a plurality of regions having an average pixel intensity;
compute an average pixel intensity of the enclosed first eye color defect region, and a number of neighborhood regions having average pixel intensity lesser than a second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region; and
determine presence of an eye color defect at the computed first eye color defect region upon determining the number of neighborhood regions having an average pixel intensity less than the second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region being greater than a second predetermined threshold.
7. The apparatus of claim 6 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
compute a first difference image for a first eye region based on difference of a red pixel intensity and a green pixel intensity of each of a first set of pixels associated with the first eye region; and
determine the first eye color defect region based on the computing.
8. The apparatus of claim 7 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
compute a second difference image based on:
a difference of red pixel intensity and green pixel intensity of a second set of pixels, and
an intensity level of the second set of pixels, the second set of pixels associated with a second eye region;
determine a second eye color defect region, if the first eye region fails in the verification; and
correct the eye color defect at the computed second eye color defect region.
9. The apparatus of claim 6 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
perform a verification based on a shape of the first eye color defect region upon verifying presence of the eye color defect at the computed first eye color defect region.
10. The apparatus of claim 6 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
correct the eye color defect at the determined first eye color defect region upon verifying presence of the eye color defect at the determined first eye color defect region.
11. A computer program product comprising at least one computer-readable storage medium, the computer-readable storage medium comprising a set of instructions configured to cause an apparatus to at least:
compute a smallest bounding rectangle for enclosing a first eye color defect region;
divide a neighborhood region of the smallest bounding rectangle into a plurality of regions having an average pixel intensity;
compute an average pixel intensity of the enclosed first eye color defect region, and a number of neighborhood regions having average pixel intensity lesser than a second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region; and
determine presence of an eye color defect at the computed first eye color defect region upon determining the number of neighborhood regions having an average pixel intensity less than the second predetermined fraction of the average pixel intensity of the enclosed first eye color defect region being greater than a second predetermined threshold.
12. The computer program product of claim 11 , wherein the set of instructions are further configured to cause the apparatus at least to perform:
compute a first difference image for a first eye region based on difference of a red pixel intensity and a green pixel intensity of each of a first set of pixels associated with the first eye region; and
determine the first eye color defect region based on the computing.
13. The computer program product of claim 12 , wherein the set of instructions are further configured to cause the apparatus at least to perform:
compute a second difference image based on:
a difference of red pixel intensity and a green pixel intensity of a second set of pixels, and
an intensity level of the second set of pixels associated with a second eye region;
determine a second eye color defect region, if the first eye region fails in the verification; and
correct the eye color defect at the computed second eye color defect region.
14. The computer program product of claim 11 , wherein the set of instructions are further configured to cause the apparatus at least to perform:
perform a verification based on a shape of the first eye color defect region upon verifying presence of the eye color defect at the computed first eye color defect region.
15. The computer program product of claim 11 , wherein the set of instructions are further configured to cause the apparatus at least to perform:
correct the eye color defect at the determined first eye color defect region upon verifying presence of the eye color defect at the determined first eye color defect region.