Spoof detection for biometric authentication
This specification describes technologies relating to biometric authentication based on images of the eye. In general, one aspect of the subject matter described in this specification can be embodied in methods that include obtaining images of a subject including a view of an eye. The methods may further include determining a behavioral metric based on detected movement of the eye as the eye appears in a plurality of the images, determining a spatial metric based on a distance from a sensor to a landmark that appears in a plurality of the images each having a different respective focus distance, and determining a reflectance metric based on detected changes in surface glare or specular reflection patterns on a surface of the eye. The methods may further include determining a score based on the behavioral, spatial, and reflectance metrics and rejecting or accepting the one or more images based on the score.
1. A computer-implemented method comprising:
capturing, using a light sensor, a two or more images of a subject including a view of an eye of the subject while changing a focus distance of the light sensor at different times and according to a pattern such that a plurality of the images have different respective focus distances;
detecting a respective degree of focus for each of a plurality of the images;
calculating a first metric based on a determination of whether the detected respective degrees of focus correspond to the pattern;
calculating, for each of two or more landmarks, a respective distance of the landmark to the sensor based on respective degrees of focus of the landmark in a plurality of the images;
calculating a second metric based on a determination of whether the landmarks lie in a same plane based on the respective distances; and
rejecting or accepting the images based on, at least, the first metric and the second metric.
2. The method of claim 1 wherein a particular focus distance is a distance from the sensor to a point in a field of view of the sensor that is in focus.
3. The method of claim 1 wherein detecting the respective degree of focus of the image comprises measuring an extent that a landmark in the image is blurred.
4. The method of claim 3 wherein measuring the extent that the landmark in the image is blurred comprises identifying a quantity of high frequency components of the image in a vicinity of the landmark.
5. The method of claim 1 wherein the landmark is one of an iris, an eye corner, a nose, and an ear.
6. The method of claim 1 comprising changing a white balance or an exposure time of the light sensor at different times during the capturing and according to a second pattern such that a plurality of the images have different respective white balances or different respective exposure times.
7. The method of claim 6 wherein rejecting or accepting the images based on, at least, the first metric comprises:
detecting a respective white balance or a respective exposure time for each of a plurality of the images;
calculating a second metric based on a determination of whether the detected respective white balances or respective exposure times correspond to the second pattern; and
rejecting or accepting the images based on the first metric and the second metric.
8. The method of claim 1 wherein rejecting or accepting the images based on, at least, the first metric comprises:
providing the first metric and one or more second metrics to a trained function approximator that was trained using training images and the first and second metrics as applied to the training images; and
rejecting or accepting the images based on an output of the function approximator.
9. The method of claim 8 wherein a particular second metric is based on one of: a measure of deviation of detected movement of the eye from expected movement of the eye as the eye appears in a plurality of the images, and changes in glare or specular reflection patterns on a surface of the eye as the eye appears in a plurality of the images.
10. The method of claim 9 wherein the detected movement of the eye is a measure of saccadic motion.
11. The method of claim 9 wherein the detected movement of the eye is a measure of onset, duration, or acceleration of gaze transition.
12. The method of claim 1 comprising changing illumination of the subject at different times during the capturing and according to a second pattern such that a plurality of the images have different respective illuminations.
13. The method of claim 12 wherein rejecting or accepting the images based on, at least, the first metric comprises:
detecting a respective illumination changes for each of a plurality of the images;
calculating a second metric based on a determination of whether the detected illumination changes correspond to the second pattern; and
rejecting or accepting the images based on the first metric and the second metric.
14. A system comprising:
data process apparatus programmed to perform operations comprising:
capturing, using a light sensor, a two or more images of a subject including a view of an eye of the subject while changing a focus distance of the light sensor at different times and according to a pattern such that a plurality of the images have different respective focus distances;
detecting a respective degree of focus for each of a plurality of the images;
calculating a first metric based on a determination of whether the detected respective degrees of focus correspond to the pattern;
calculating, for each of two or more landmarks, a respective distance of the landmark to the sensor based on respective degrees of focus of the landmark in a plurality of the images;
calculating a second metric based on a determination of whether the landmarks lie in a same plane based on the respective distances; and
rejecting or accepting the images based on, at least, the first metric and the second metric.
15. The system of claim 14 wherein a particular focus distance is a distance from the sensor to a point in a field of view of the sensor that is in focus.
16. The system of claim 14 wherein detecting the respective degree of focus of the image comprises measuring an extent that a landmark in the image is blurred.
17. The system of claim 16 wherein measuring the extent that the landmark in the image is blurred comprises identifying a quantity of high frequency components of the image in a vicinity of the landmark.
18. The system of claim 14 wherein the landmark is one of an iris, an eye corner, a nose, and an ear.
19. The system of claim 14 comprising changing a white balance or an exposure time of the light sensor at different times during the capturing and according to a second pattern such that a plurality of the images have different respective white balances or different respective exposure times.
20. The system of claim 19 wherein rejecting or accepting the images based on, at least, the first metric comprises:
detecting a respective white balance or a respective exposure time for each of a plurality of the images;
calculating a second metric based on a determination of whether the detected respective white balances or respective exposure times correspond to the second pattern; and
rejecting or accepting the images based on the first metric and the second metric.
21. The system of claim 14 wherein rejecting or accepting the images based on, at least, the first metric comprises:
providing the first metric and one or more second metrics to a trained function approximator that was trained using training images and the first and second metrics as applied to the training images; and
rejecting or accepting the images based on an output of the function approximator.
22. The system of claim 21 wherein a particular second metric is based on one of: a measure of deviation of detected movement of the eye from expected movement of the eye as the eye appears in a plurality of the images, and changes in glare or specular reflection patterns on a surface of the eye as the eye appears in a plurality of the images.
23. The system of claim 22 wherein the detected movement of the eye is a measure of saccadic motion.
24. The system of claim 22 wherein the detected movement of the eye is a measure of onset, duration, or acceleration of gaze transition.
25. The system of claim 14 comprising changing illumination of the subject at different times during the capturing and according to a second pattern such that a plurality of the images have different respective illuminations.
26. The system of claim 25 wherein rejecting or accepting the images based on, at least, the first metric comprises:
detecting a respective illumination changes for each of a plurality of the images;
calculating a second metric based on a determination of whether the detected illumination changes correspond to the second pattern; and
rejecting or accepting the images based on the first metric and the second metric.
27. A computer program stored on a non-transitory computer-readable storage medium that, when executed by data processing apparatus, causes the data processing apparatus to perform operations comprising:
capturing, using a light sensor, a two or more images of a subject including a view of an eye of the subject while changing a focus distance of the light sensor at different times and according to a pattern such that a plurality of the images have different respective focus distances;
detecting a respective degree of focus for each of a plurality of the images;
calculating a first metric based on a determination of whether the detected respective degrees of focus correspond to the pattern;
calculating, for each of two or more landmarks, a respective distance of the landmark to the sensor based on respective degrees of focus of the landmark in a plurality of the images;
calculating a second metric based on a determination of whether the landmarks lie in a same plane based on the respective distances; and
rejecting or accepting the images based on, at least, the first metric and the second metric.
28. The system of claim 27 wherein a particular focus distance is a distance from the sensor to a point in a field of view of the sensor that is in focus.