Authentication of a user for access

1 . A method for authenticating a user for access to a vehicle comprising:

a. receiving an access request from a mobile user device within a threshold proximity of the vehicle, the access request including a template,

b. in response to the access request, recording an image,

c. extracting at least one facial feature of the image,

d. detecting skin within the image,

e. in response to said detecting skin and to a feature vector of the at least one facial feature being within a threshold distance of a corresponding template feature of the template, generating an access signal indicative of the user having access to the vehicle, and

f. controlling one or more components of the vehicle using the access signal.

2 . The method according to claim 1 , wherein said recording comprises recording the image by a device integrated into the vehicle.

3 . The method according to claim 2 , wherein said recording comprises recording the image by a device integrated into a B-pillar.

4 . The method according to claim 1 , wherein said controlling comprises starting the motor of the vehicle.

5 . The method according to claim 1 , wherein said controlling comprises unlocking the door of the vehicle.

6 . The method according to claim 1 , wherein the vehicle is a car.

7 . The method according to claim 1 , wherein the image comprises a reflection pattern generated in response to illumination with patterned light.

8 . The method according to claim 7 , wherein the illumination is in a range of from 700 nm to 1100 nm.

9 . The method according to claim 8 , wherein the illumination comprises a cloud of periodic dots.

10 . The method according to claim 8 , wherein the illumination is effected by a projector comprising an array of vertical cavity surface emitting lasers.

11 . The method according to claim 1 , wherein the illumination comprises a cloud of periodic dots.

12 . The method according to claim 1 , wherein said detecting skin is based on an image comprising a reflection pattern.

13 . The method according to claim 12 , wherein said detecting skin is based on several partial images obtained by cropping the image.

14 . The method according to claim 13 , wherein said detecting skin is based on a data-driven model which is parametrized to receive images containing a reflection feature and to output the likelihood if the reflection feature is skin or not.

15 . The method according to claim 14 , wherein the data-driven model is a neural network.

16 . The method according to claim 1 , wherein said recording comprises recording more than one image.

17 . The method according to claim 16 , wherein one of the images is an image suitable for extracting at least one facial feature and another image is suitable for said detecting skin.

18 . The method according to claim 1 , wherein the access signal is generated using a matching score as a measure for the distance between the facial feature and the template.

19 . The method according to claim 17 , wherein the image suitable for extracting at least one facial feature is selected based on the number of datapoints in the image.

20 . A method for authenticating a user for access to a vehicle comprising:

a. receiving an access request from a mobile user device within a threshold proximity of the vehicle, the access request including user data,

b. in response to the access request, recording an image,

c. based on the user data, selecting, from a plurality of templates, a template;

d. extracting at least one facial feature of the image,

e. detecting skin within the image,

f. in response to said detecting skin and to the at least one facial feature being within a threshold matching range of the template, generating an access signal indicative of the user having access to the vehicle, and

g. controlling one or more components of the vehicle using the access signal.