Method and apparatus of correcting hybrid flash artifacts in digital images
View Patent ↗A method for digital image eye artifact detection and correction include identifying one or more candidate red-eye defect regions in an acquired image. For one or more candidate red-eye regions, a seed pixels and/or a region of pixels having a high intensity value in the vicinity of the candidate red-eye region is identified. The shape, roundness or other eye-related characteristic of a combined hybrid region including the candidate red-eye region and the region of high intensity pixels is analyzed. Based on the analysis of the eye-related characteristic of the combined hybrid region, it is determined whether to apply flash artifact correction, including red eye correction of the candidate red-eye region and/or correction of the region of high intensity pixels.
1. A digital image acquisition device comprising:
a lens;
an image sensor;
a processor; and
a computer readable medium having computer readable code embodied therein for programming the processor to analyze a digital image for segmenting an iris region from one or more adjacent sub-regions of an identified eye region within the image, wherein the device is configured to:
acquire a digital image;
identify a candidate eye region in said image;
determine one or more sub-regions of the candidate eye region each having an intensity value that is above or below one or more threshold intensity values;
identify an iris region and one or more adjacent sub-regions based on discerning chrominance values of pixels of the iris region and the one or more adjacent sub-regions; and
determine the iris region based on analyzing one or more chrominance values of pixels of at least one of the adjacent sub-regions.
2. The device of claim 1 , the device being further configured to analyze a shape characteristic of the one or more sub-regions.
3. The device of claim 1 , wherein said device is further configured to analyze said acquired image in Luminance chrominance color space and said image comprises a region of high intensity pixels having a luminance value greater than a luminance threshold.
4. The device of claim 3 , wherein said region of high intensity pixels has blue-yellow chrominance values greater than a chrominance threshold.
5. The device of claim 4 , wherein said region of high intensity pixels has a red-green value less than a red-green threshold.
6. The device of claim 1 , wherein said device is further configured to analyze an eye-related characteristic comprising at least one of shape, roundness and pupil size.
7. A non-transitory computer readable medium having computer readable code embodied therein for programming one or more processors to analyze an acquired digital image for segmenting an iris region from one or more adjacent sub-regions of an identified eye region within the image, wherein the code is configured to program the one or more processors to:
identify a candidate eye region in said image;
determine one or more sub-regions of the candidate eye region each having an intensity value that is above or below one or more threshold intensity values;
identify an iris region and one or more adjacent sub-regions based on discerning chrominance values of pixels of the iris region and the one or more adjacent sub-regions; and
determine the iris region based on analyzing one or more chrominance values of pixels of at least one of the adjacent sub-regions.
8. The non-transitory computer readable medium of claim 7 , the code being further configured to program the one or more processors to analyze a shape characteristic of the one or more sub-regions to further determine the iris region.
9. The non-transitory computer readable medium of claim 7 , the code being further configured to program the one or more processors to analyze said acquired image in Luminance chrominance color space and said image comprises a region of high intensity pixels having a luminance value greater than a luminance threshold.
10. The non-transitory computer readable medium of claim 9 , wherein said region of high intensity pixels has blue-yellow chrominance values greater than a chrominance threshold.
11. The non-transitory computer readable medium of claim 10 , wherein said region of high intensity pixels has a red-green value less than a red-green threshold.
12. The non-transitory computer readable medium of claim 7 , the code being further configured to program the one or more processors to analyze an eye-related characteristic comprising at least one of shape, roundness and pupil size to determine the iris region.
13. A method of segmenting an iris region from one or more adjacent sub-regions of an identified eye region within an acquired digital image, comprising
acquiring a digital image;
identifying a candidate eye region in said image;
determining one or more sub-regions of the candidate eye region each having an intensity value that is above or below one or more threshold intensity values;
identifying an iris region and one or more adjacent sub-regions based on discerning chrominance values of pixels of the iris region and the one or more adjacent sub-regions; and
determining the iris region based on analyzing one or more chrominance values of pixels of at least one of the adjacent sub-regions.
14. The method of claim 13 , further comprising analyzing a shape characteristic of the one or more sub-regions to further determine the iris region.
15. The method of claim 13 , further comprising analyzing said acquired image in Luminance chrominance color space and said image comprises a region of high intensity pixels having a luminance value greater than a luminance threshold.
16. The method of claim 15 , wherein said region of high intensity pixels has blue-yellow chrominance values greater than a chrominance threshold.
17. The method of claim 16 , wherein said region of high intensity pixels has a red-green value less than a red-green threshold.
18. The method of claim 13 , further comprising analyzing an eye-related characteristic comprising at least one of shape, roundness and pupil size.