Granted Patent B2

US 9,355,456 · App. 13/807,551 · Granted May 31, 2016

Abstract

Claims (61)

1. A method comprising:

computing a first difference image based on a difference between red pixel intensity and green pixel intensity of a set of pixels, the set of pixels being associated with a first eye region of an image, wherein the first eye region comprises a plurality of quadrantal regions; and the set of pixels comprise at least one pixel of an eye color defect region of at least one of the plurality of quadrantal regions of the first eye region and at least one pixel from a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye region;

processing the first difference image for computing at least one gradient and at least one projection associated with one or more gradient, wherein the one or more gradient comprises a first order gradient in a first direction and a first order gradient in a second direction different than the first direction;

determining at least one central point based on the at least one projection; and

computing the first eye color defect region based on the at least one central point and a plurality of red pixels of the set of pixels.

2. The method of claim 1 , wherein the image is a low resolution (LR) image.

3. The method of claim 1 , wherein the at least one projection comprises at least one horizontal projection, and at least one vertical projection associated with the at least one gradient.

4. The method of claim 1 , wherein determining the at least one central point comprises determining at least one significant peak of the at least one projection, and wherein a pixel location corresponding to the at least one significant peak is the at least one central point of the first eye color defect region.

5. The method of claim 1 further comprising performing one or more verifications of a presence of a first eye color defect in the first eye color defect region when the first eye color defect region is computed.

6. The method of claim 5 further comprising determining a confidence indicator for indicating presence of the first eye color defect at the first eye color defect region,

wherein the first eye color defect is determined to be present in the first eye color defect region when the confidence indicator is more than a first predetermined threshold, and

wherein the first eye color defect is determined to be absent in the first eye color defect region when the confidence indicator is less than a second predetermined threshold.

7. A method comprising:

determining a first eye color defect region in a low resolution (LR) image, the LR image being produced from a high resolution (HR) image, wherein the first eye color defect region comprises a plurality of quadrantal regions;

determining an eye color defect information for the LR image, the eye color defect information comprising a set of identifiers associated with a plurality of first peripheral portions of the first eye color defect region in the LR image, wherein the set of identifiers comprises at least one intensity value of an eye defect portion of at least one of the plurality of quadrantal regions of the first eye color defect region and at least one intensity value of a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye color defect region;

mapping the eye color defect information computed from the LR image to be applicable on the HR image, the HR image comprising:

a second eye color defect region corresponding to the at least one of the plurality of quadrantal regions of the first eye color defect region in the LR image; and

a plurality of second peripheral portions of the second eye color defect region corresponding to a plurality of first peripheral portions of the first eye color defect region; and

processing the HR image to identify an eye color defect in at least one of the plurality of the second peripheral portions based on the set of identifiers.

8. An apparatus comprising:

at least one processor; and

at least one memory comprising 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 first difference image based on a difference between red pixel intensity and green pixel intensity of a set of pixels, the set of pixels being associated with a first eye region of an image, wherein the first eye region comprises a plurality of quadrantal regions; and the set of pixels comprise at least one pixel of an eye color defect region of at least one of the plurality of quadrantal regions of the first eye region and at least one pixel from a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye region;

process the first difference image for computing at least one gradient and at least one projection associated with one of more gradient, wherein the one or more gradient comprises a first order gradient in a first direction and a first order gradient in a second direction different than the first direction;

determine at least one central point based on the at least one projection; and

compute the first eye color defect region based on the at least one central point and a plurality of red pixels of the set of pixels.

9. The apparatus of claim 8 , wherein the image is a low resolution (LR) image.

10. The apparatus of claim 8 , wherein the at least one projection comprises at least one horizontal projection, and at least one vertical projection associated with the at least one gradient.

11. The apparatus of claim 8 , wherein the apparatus is further caused, at least in part, to determine the at least one central point by determining at least one significant peak of the at least one projection, and wherein a pixel location corresponding to the at least one significant peak being the at least one central point of the first eye color defect region.

12. The apparatus of claim 8 , wherein the apparatus is further caused, at least in part, to perform one or more verifications of a presence of a first eye color defect in the first eye color defect region when the first eye color defect region is computed.

13. The apparatus of claim 12 , wherein the apparatus is further caused, at least in part, to determine a confidence indicator for indicating presence of a first eye color defect at the first eye color defect region,

wherein the first eye color defect is determined to be present in the first eye color defect region when the confidence indicator is more than a first predetermined threshold, and

wherein the first eye color defect is determined to be absent in the first eye color defect region when the confidence indicator is less than a second predetermined threshold.

14. An apparatus comprising:

at least one processor; and

at least one memory comprising 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:

determine a first eye color defect region in a low resolution (LR) image, the LR image being produced from a high resolution (HR) image, wherein the first eye color defect region comprises a plurality of quadrantal regions;

determine an eye color defect information for the LR image, the eye color defect information comprising a set of identifiers associated with a plurality of first peripheral portions of the first eye color defect region in the LR image, wherein the set of identifiers comprises at least one intensity value of an eye defect portion of at least one of the plurality of quadrantal regions of the first eye color defect region and at least one intensity value of a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye color defect region;

map the eye color defect information computed from the LR image to be applicable on the HR image, the HR image comprising:

a second eye color defect region corresponding to the at least one of the plurality of quadrantal regions of the first eye color defect region in the LR image; and

a plurality of second peripheral portions of the second eye color defect region corresponding to a plurality of first peripheral portions of the first eye color defect region; and

process the HR image to identify an eye color defect in at least one of the plurality of the second peripheral portions based on the set of identifiers.

15. A computer program product comprising at least one non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising a set of instructions, which, when executed by one or more processors, cause an apparatus to at least perform:

computing a first difference image based on a difference between red pixel intensity and green pixel intensity of a set of pixels, the set of pixels being associated with a first eye region of an image, wherein the first eye region comprises a plurality of quadrantal regions; and the set of pixels comprise at least one pixel of an eye color defect region of at least one of the plurality of quadrantal regions of the first eye region and at least one pixel from a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye region;

processing the first difference image for computing at least one gradient and at least one projection associated with one of more gradient, wherein the one or more gradient comprises a first order gradient in a first direction and a first order gradient in a second direction different than the first direction;

determining at least one central point based on the at least one projection; and

computing the first eye color defect region based on the at least one central point and a plurality of red pixels of the set of pixels.

16. The computer program product of claim 15 , wherein the image is a LR image.

17. The computer program product of claim 15 , wherein the at least one projection comprises at least one horizontal projection, and at least one vertical projection associated with the at least one gradient.

18. The computer program product of claim 15 , wherein the apparatus is further caused, at least in part, to determine the at least one central point by determining at least one significant peak of the at least one projection, and wherein a pixel location corresponding to the at least one significant peak being the at least one central point of the first eye color defect region.

19. The computer program product of claim 15 , wherein the apparatus is further caused, at least in part, to perform one or more verifications of a presence of a first eye color defect in the first eye color defect region when the first eye color defect region is computed.

20. The computer program product of claim 19 , wherein the apparatus is further caused, at least in part, to determine a confidence indicator for indicating presence of the first eye color defect at the first eye color defect region,

wherein the first eye color defect is determined to be present in the first eye color defect region when the confidence indicator is more than a first predetermined threshold, and

wherein the first eye color defect is determined to be absent in the first eye color defect region when the confidence indicator is less than a second predetermined threshold.

21. A computer program product comprising at least one non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising a set of instructions, which, when executed by one or more processors, cause an apparatus to at least perform:

determining a first eye color defect region in a low resolution (LR) image, the LR image being produced from a high resolution (HR) image, wherein the first eye color defect region comprises a plurality of quadrantal regions;

determining an eye color defect information for the LR image, the eye color defect information comprising a set of identifiers associated with a plurality of first peripheral portions of the first eye color defect region in the LR image, wherein the set of identifiers comprises at least one intensity value of an eye defect portion of at least one of the plurality of quadrantal regions of the first eye color defect region and at least one intensity value of a non-defect eye portion of the at least one of the plurality of quadrantal regions of the first eye color defect region;

mapping the eye color defect information computed from the LR image to be applicable on the HR image, the HR image comprising:

a second eye color defect region corresponding to the at least one of the plurality of quadrantal regions of the first eye color defect region in the LR image; and

a plurality of second peripheral portions of the second eye color defect region corresponding to a plurality of first peripheral portions of the first eye color defect region; and

processing the HR image to identify an eye color defect in at least one of the plurality of the second peripheral portion based on the set of identifiers.

Assignments (12)