System and method for ocular recognition

1. A method comprising:

decomposing via a computer an ocular region into several filtered images of different orientation and scale;

using the computer to combine the decomposed images for each scale;

using a computer executed classifier for each scale, matching across different quality images; and

using a computer, constructing a matching score by combining the scale scores using adaptively weighted sum for each scale.

2. The method of claim 1 wherein decomposing the ocular region comprises using a Gabor filter bank with discriminatively tuned parameters.

3. The method of claim 1 wherein decomposing the ocular region comprises using a Log Gabor filter bank with discriminatively tuned parameters.

4. The method of claim 1 wherein the classifier comprises a fisher classifier.

5. The method of claim 1 wherein the weights are based on energy of each scale normalized by a total energy of all scales.

6. The method of claim 1 wherein the weights are based on an ocular quality measure.

7. A system comprising:

a module to decompose via a computer an ocular region into several filtered images of different orientation and scale;

a module to use the computer to combine the decomposed images for each scale;

a module to use a computer executed classifier for each scale, matching across different quality images; and

a module to use a computer to construct a matching score by combining the scale scores using adaptively weighted sum for each scale.

8. The system of claim 7 wherein decomposing the ocular region comprises using a Gabor filter bank or Log Gabor filter bank with discriminatively tuned parameters.

9. The system of claim 8 wherein the classifier comprises a fisher classifier.

10. The method of claim 1 wherein the weights are based on energy of each scale normalized by a total energy of all scales.