Iris recognition using localized Zernike moments
A system receives an iris image and segments the iris region. The segmented iris region is mapped to a unit disk and partitioned into local iris regions (or sectors) as a function of the radius and angle The system calculates localized Zernike moments for a plurality of regions of the unit disk. The localized Zernike moment includes a projection of the local iris region into a space of Zernike polynomial orthogonal basis functions. The system generates an iris feature set from the localized Zernike moments for each partitioned region, excluding the regions which are comprised by occlusion. The iris features are weighted based on the conditions of blur, gaze and occlusion of the iris region. A probe iris image is then matched to a plurality of iris images in a database based on the distance of its feature set to the corresponding plurality of iris feature sets.
1. A system comprising:
a computer processor and computer storage device configured to:
receive an image of an iris;
segment the image of the iris, thereby creating a local iris region;
map the image of the iris as a unit disk starting at an inner boundary of the iris and stopping at an outer boundary of the iris;
segment the unit disk as a function of a plurality of Gaussians centered at different locations in the local iris region, thereby generating a plurality of iris sub-regions;
calculate a localized Zernike moment for each of the plurality of iris sub-regions to obtain a plurality of localized Zernike moments, each localized Zernike moment comprising a projection of the local iris region into a space of Zernike polynomial orthogonal basis functions;
select the localized Zernike moments calculated for the iris sub-regions such that the iris sub-regions are not compromised by occlusion;
generate a local iris texture feature set using the selected localized Zernike moments calculated for one or more iris sub-regions;
classify the image of the iris as a function of the local iris texture feature set; and
compare the classified image of the iris to a plurality of iris images in a database.
2. The system of claim 1 , wherein the computer processor is configured to generate the local iris texture feature set from a vector of localized Zernike moments.
3. The system of claim 1 , wherein the classifying of the image comprises determining a minimum distance between iris features.
4. The system of claim 1 , wherein the classifying the image comprises determining a total distance, wherein the total distance comprises a weighted sum of the distances between the iris features.
5. The system of claim 4 , wherein the weighted sum is a function of an occlusion, a blur, or a gaze condition of one or more of a target iris image, a probe iris image, and a matching iris image.
6. The system of claim 5 , wherein the weighted sum comprises a product of individual weights that are related to occlusion, blur, and gaze.
7. The system of claim 1 , wherein a distance between iris features comprises one or more of a Euclidean distance and a city block distance between the localized Zernike moments.
8. The system of claim 1 , wherein the image of the iris is received from an iris acquisition system or a database of iris images.
9. The system of claim 1 , wherein the calculation of the localized Zernike moments is a function of a discriminate selection using an offline boosting method.
10. A process comprising:
receiving an image of an iris;
segmenting the image of the iris, thereby creating a local iris region;
mapping the image of the iris as a unit disk starting at an inner boundary of the iris and stopping at an outer boundary of the iris;
segmenting the unit disk as a function of a plurality of Gaussians centered at different locations in the local iris region, thereby generating a plurality of iris sub-regions;
calculating a localized Zernike moment for each iris sub-region to obtain a plurality of localized Zernike moments, each localized Zernike moment comprising a projection of the local iris region into a space of Zernike polynomial orthogonal basis functions;
selecting the localized Zernike moments computed for the iris sub-regions such that the iris sub-regions are not compromised by occlusion;
generating a local iris texture feature set using the selected Zernike moments;
classifying the image of the iris as a function of the local iris texture feature set; and
comparing the classified image of the iris to a plurality of iris images in a database.
11. The process of claim 10 , comprising generating the local iris texture feature set from a vector of localized Zernike moments.
12. The process of claim 10 , wherein the classifying of the image comprises determining a minimum distance between iris features.
13. The process of claim 10 , wherein the classifying the image comprises determining a total distance, wherein the total distance comprises a weighted sum of the distances between the iris features.
14. The process of claim 13 , wherein the weighted sum is a function of an occlusion, a blur, or a gaze condition of one or more of a target iris image, a probe iris image, and a matching iris image; and wherein the weighted sum comprises a product of individual weights that are related to occlusion, blur, and gaze.
15. The process of claim 10 , wherein a distance between iris features comprises one or more of a Euclidean distance and a city block distance between the localized Zernike moments.
16. The process of claim 10 , wherein the image of the iris is received from an iris acquisition system or a database of iris images.
17. A system comprising:
a computer processor and computer storage device configured to:
receive an image of an iris;
map the image of the iris as a unit disk starting at an inner boundary of the iris and stopping at an outer boundary of the iris;
segment the unit disk as a function of a plurality of Gaussians centered at different locations in an iris region, thereby generating a plurality of iris sub-regions;
calculate a localized Zernike moment for each iris sub-region to obtain a plurality of localized Zernike moments;
select the localized Zernike moments computed for the iris sub-regions such that the iris sub-regions are not compromised by occlusion; and
generate the local iris texture feature set using the selected Zernike moments computed over one or more iris sub-regions.
18. The system of claim 17 , wherein the calculation of the localized Zernike moments is a function of a discriminate selection using an offline boosting method.