Eye tracking

1 . A method of determining a presence of a tear in an eye of a user of an eye tracking system, the method comprising:

receiving an image of the eye of the user;

processing the image to identify one or more features of the image, wherein the one or more features comprises an edge of the pupil or iris of the eye of the user;

processing the image to determine a circularity of the edge of the pupil or iris;

comparing the one or more identified features to one or more expected features, wherein the one or more expected features are based on a known spatial relationship between at least one component of the eye tracking system and the eye of the user, and wherein comparing comprises comparing the determined circularity to an expected circularity;

determining that a tear is present in the eye of the user based on the comparison, wherein the determination that a tear is present is made if a difference between the determined circularity and the expected circularity is above a threshold; and

altering an eye tracking algorithm to take account of the tear by discarding image data associated with the tear; or

altering an eye tracking algorithm to take account of the tear by applying a correction factor to account for optical distortion caused by the tear.

2 . The method of claim 1 , wherein the one or more features of the image comprises an edge of the pupil or iris of the eye of the user.

3 . The method of claim 1 , wherein the one or more features of the image comprises a glint pattern comprising one or more glints, the method comprising:

processing the image to determine a position of at least one glint of the glint pattern;

determining a distance between the determined position of at least one glint and an expected position of the at least one glint; and

determining that a tear is present in the eye of the user if the determined distance is above a threshold.

4 . The method of claim 1 , comprising providing the image to an image recognition algorithm, wherein the image recognition algorithm is trained to identify images of eyes with a tear present.

5 . The method of claim 1 , further comprising one of:

generating an alert that a tear is present in the eye of the user;

generating a confidence value for an output of the eye tracking system based on the presence of the tear.

6 . An eye tracking system for determining a presence of a tear in an eye of a user, the system comprising:

an image sensor configured to capture an image of the eye of the user; and

an image processing module configured to:

process the captured image to identify one or more features of the image, wherein the one or more features comprises an edge of the pupil or iris of the eye of the user;

process the captured image to determine a circularity of the edge of the pupil or iris;

compare the one or more identified features to one or more expected features, wherein the one or more expected features are based on a known spatial relationship between at least one component of the eye tracking system and the eye of the user, and wherein comparing comprises comparing the determined circularity to an expected circularity; and

determine that a tear is present in the eye of the user based on the comparison, wherein the determination that a tear is present is made if a difference between the determined circularity and the expected circularity is above a threshold; and

altering an eye tracking algorithm to take account of the tear by discarding image data associated with the tear; or

altering an eye tracking algorithm to take account of the tear by applying a correction factor to account for optical distortion caused by the tear.

7 . The eye tracking system of claim 6 , wherein the one or more features of the image comprises a glint pattern comprising one or more glints, wherein the image processing module is configured to:

process the captured image to determine a position of at least one glint of the glint pattern;

determine a distance between the determined position of at least one glint and an expected position of the at least one glint; and

determine that a tear is present in the eye of the user if the determined distance is above a threshold.

8 . The eye tracking system of claim 6 , wherein the image processing module is configured to provide the captured image to an image recognition algorithm, wherein the image recognition algorithm is trained to identify images of eyes with a tear present.

9 . The eye tracking system of claim 6 , wherein the image processing module is configured to perform at least one of:

generating an alert that a tear is present in the eye of the user;

generating a confidence value for an eye tracking result based on the presence of the tear.

10 . The eye tracking system of claim 6 , further comprising at least one illuminator configured to illuminate the eye of the user of the eye tracking system, wherein the illuminator is arranged at a fixed position relative to the image sensor and/or the eye of the user.

11 . A head-mountable device comprising:

at least one illuminator configured to illuminate an eye of the user;

an image sensor configured to capture an image of the eye of the user; and

an image processing module configured to:

process the captured image to identify one or more features of the image, wherein the one or more features comprises an edge of the pupil or iris of the eye of the user;

process the captured image to determine a circularity of the edge of the pupil or iris;

compare the one or more identified features to one or more expected features, wherein the one or more expected features are based on a known spatial relationship between the at least one illuminator, the image sensor, and the eye of the user, and wherein comparing comprises comparing the determined circularity to an expected circularity; and

determine that a tear is present in the eye of the user based on the comparison, wherein the determination that a tear is present is made if a difference between the determined circularity and the expected circularity is above a threshold; and

altering an eye tracking algorithm to take account of the tear by discarding image data associated with the tear; or

altering an eye tracking algorithm to take account of the tear by applying a correction factor to account for optical distortion caused by the tear.