Method of image-based user authentication

• US 8,655,027 B1
• Filed: 03/25/2011
• Issued: 02/18/2014
• Est. Priority Date: 03/25/2011
• Status: Active Grant

• Current Assignee: The United States of America As Represented By The Director National Security Agency
• Original Assignee: The United States of America As Represented By The Director National Security Agency
• Inventors: Olthoff, Kenneth G.
• Primary Examiner(s): Repko, Jason M
• Assistant Examiner(s): Rowland, Jhere
• Application Number:
  US13/066,853
• Time in Patent Office: 1,061 Days
• Field of Search: None
• US Class Current: 382/118
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 21/00 Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/36 by graphic or iconic representation
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

A method of authenticating a user by capturing an image of the user, assigning a user-name, selecting an image category, selecting a pattern, selecting locations on the user'"'"'s face, assigning a rotation-value, logging onto a computer, presenting images, where some images are in the image category, selecting images that are the pattern away from the images in the image category, calculating a rotation angle, projecting the selected images that are rotated by the rotation angle onto the user'"'"'s face at the locations, capturing an image of the user'"'"'s face with the rotated images projected thereon, and authenticating the user if the user'"'"'s facial features match the user'"'"'s face and the projected images are the pattern away from the images in the image-category, are at the locations, are rotated by the rotation angle, and exhibit distortion consistent with the contour of the user'"'"'s face.

Claims

1. A method of authenticating a computer user, comprising the steps of:

a) capturing on a computing device a facial image of a user;

b) assigning on the computing device a user-definable user-name to the user;

c) selecting on the computing device a user-definable image category for the user;

d) selecting on the computing device a user-definable image-offset pattern for the user;

e) selecting on the computing device at least two user-definable locations on the user'"'"'s face;

f) assigning on the computing device a user-definable rotation-value to the user;

g) logging onto the computing device by the user using the user'"'"'s user-name;

h) presenting to the user on the computing device a time and a grid of a plurality of images, where at least two of the images are in the user-definable image category selected in step (c);

i) selecting on the computing device by the user at least two images in the grid of images that are at the offset pattern from each of the at least two images in the image category selected in step (c);

j) calculating on the computing device an image-rotation angle that is a function of the rotation value assigned in step (f) and the time presented in step (h);

k) projecting the images selected in step (i) onto the user'"'"'s face at the at least two locations selected in the step (e), where each projected image is rotated by the image-rotation angle calculated in step (j);

l) capturing on the computing device an image of the user'"'"'s face after the operation of step (k); and

m) authenticating the user on the computing device if the user'"'"'s facial features captured in step (l) match the user'"'"'s face captured in step (a), the images projected onto the use'"'"'s face that were captured in step (l) are images in the grid that are the offset-pattern away from images in the grid that are in the image-category selected in step (c), the images projected onto the user'"'"'s face that were captured in step (l) are at locations on the user'"'"'s face that were selected in step (e), the images projected onto the user'"'"'s face that were captured in step (l) are rotated within a user-definable tolerance from a twelve o'"'"'clock position at the image-rotation angle calculated in step (j), and the images projected onto the user'"'"'s face that were captured in step (l) exhibit a user-definable amount of distortion due to the contour of the user'"'"'s face as compared to how the images would appear on a flat surface.

2. The method of claim 1, wherein said step of selecting on the computing device a user-definable image-offset pattern for the user is comprised of selecting on the computing device an image-offset pattern for the user that is two positions to the left and one position up, where the image-offset pattern wraps around an edge of the grid when necessary.

3. The method of claim 1, wherein said step of assigning on the computing device a user-definable rotation-value to the user is comprised of assigning on the computing device an integer to the user.

4. The method of claim 1, wherein said step of presenting to the user on the computing device a time and a grid of a plurality of images, where at least two of the images are in the user-definable image category selected in step (c) is comprised of presenting to the user on the computing device a current local time and a grid of 20 images in a 4 rows by 5 columns grid.

5. The method of claim 1, wherein said step of presenting to the user on the computing device a time and a grid of a plurality of images, where at least two of the images are in the user-definable image category selected in step (c) is comprised of presenting to the user on the computing device a current local time and a grid of images where not more than 50% of the images in the image grid presented to the user consist of images that appear in the last 20 image grids presented to the user, the at least two images that are in the user-definable image category may not have been used more than 5 times in the last 20 image grids presented to the user, and the at least two images that are in the user-definable image category may not have appeared in the same locations more than 5 times in the last 20 image grids presented to the user.

6. The method of claim 1, wherein said step of calculating on the computing device an image-rotation angle that is a function of the rotation value assigned in step (f) and the time presented in step (h) is comprised of calculating on the computing device an image-rotation angle where an hour of a current local time modulo 4 is a most significant bit of a three bit number, minutes of the current local time are two least significant bits in the three bit number, adding the resulting three bit number to the image rotation value, and reducing the result modulo 360.

7. The method of claim 1, wherein said step of authenticating the user on the computing device if the user'"'"'s facial features captured in step (l) match the user'"'"'s face captured in step (a), the images projected onto the use'"'"'s face that were captured in step (l) are images in the grid that are the offset-pattern away from images in the grid that are in the image-category selected in step (c), the images projected onto the user'"'"'s face that were captured in step (l) are at locations on the user'"'"'s face that were selected in step (e), the images projected onto the user'"'"'s face that were captured in step (l) are rotated within a user-definable tolerance from a twelve o'"'"'clock position at the image-rotation angle calculated in step (j), and the images projected onto the user'"'"'s face that were captured in step (l) exhibit a user-definable amount of distortion due to the contour of the user'"'"'s face as compared to how the images would appear on a flat surface is comprised of authenticating the user on the computing device if the user'"'"'s facial features captured in step (l) match the user'"'"'s face captured in step (a), the images projected onto the use'"'"'s face that were captured in step (l) are images in the grid that are the offset-pattern away from images in the grid that are in the image-category selected in step (c), the images projected onto the user'"'"'s face that were captured in step (l) are at locations on the user'"'"'s face that were selected in step (e), the images projected onto the user'"'"'s face that were captured in step (l) are rotated within plus and minus ten degrees from a twelve o'"'"'clock position at the image-rotation angle calculated in step (j), and the images projected onto the user'"'"'s face that were captured in step (l) exhibit distortion consistent with effects of the contour of the user'"'"'s face as compared to how the images would appear on a flat surface.

8. The method of claim 2, wherein said step of assigning on the computing device a user-definable rotation-value to the user is comprised of assigning on the computing device an integer to the user.

9. The method of claim 8, wherein said step of presenting to the user on the computing device a time and a grid of a plurality of images, where at least two of the images are in the user-definable image category selected in step (c) is comprised of presenting to the user on the computing device a current local time and a grid of 20 images in a 4 rows by 5 columns grid.

10. The method of claim 9, wherein said step of presenting to the user on the computing device a time and a grid of a plurality of images, where at least two of the images are in the user-definable image category selected in step (c) is comprised of presenting to the user on the computing device a current local time and a grid of images where not more than 50% of the images in the image grid presented to the user consist of images that appear in the last 20 image grids presented to the user, the at least two images that are in the user-definable image category may not have been used more than 5 times in the last 20 image grids presented to the user, and the at least two images that are in the user-definable image category may not have appeared in the same locations more than 5 times in the last 20 image grids presented to the user.

11. The method of claim 10, wherein said step of calculating on the computing device an image-rotation angle that is a function of the rotation value assigned in step (f) and the time presented in step (h) is comprised of calculating on the computing device an image-rotation angle where an hour of a current local time modulo 4 is a most significant bit of a three bit number, minutes of the current local time are two least significant bits in the three bit number, adding the resulting three bit number to the image rotation value, and reducing the result modulo 360.

12. The method of claim 11, wherein said step of authenticating the user on the computing device if the user'"'"'s facial features captured in step (l) match the user'"'"'s face captured in step (a), the images projected onto the use'"'"'s face that were captured in step (l) are images in the grid that are the offset-pattern away from images in the grid that are in the image-category selected in step (c), the images projected onto the user'"'"'s face that were captured in step (l) are at locations on the user'"'"'s face that were selected in step (e), the images projected onto the user'"'"'s face that were captured in step (l) are rotated within a user-definable tolerance from a twelve o'"'"'clock position at the image-rotation angle calculated in step (j), and the images projected onto the user'"'"'s face that were captured in step (l) exhibit a user-definable amount of distortion due to the contour of the user'"'"'s face as compared to how the images would appear on a flat surface is comprised of authenticating the user on the computing device if the user'"'"'s facial features captured in step (l) match the user'"'"'s face captured in step (a), the images projected onto the use'"'"'s face that were captured in step (l) are images in the grid that are the offset-pattern away from images in the grid that are in the image-category selected in step (c), the images projected onto the user'"'"'s face that were captured in step (l) are at locations on the user'"'"'s face that were selected in step (e), the images projected onto the user'"'"'s face that were captured in step (l) are rotated within plus and minus ten degrees from a twelve o'"'"'clock position at the image-rotation angle calculated in step (j), and the images projected onto the user'"'"'s face that were captured in step (l) exhibit distortion consistent with effects of the contour of the user'"'"'s face as compared to how the images would appear on a flat surface.