Image Based Turing Test

• US 20080066014A1
• Filed: 09/13/2007
• Published: 03/13/2008
• Est. Priority Date: 09/13/2006
• Status: Active Grant

• Current Assignee: George Mason Intellectual Properties, Inc.
• Original Assignee: George Mason Intellectual Properties, Inc.
• Inventors: Misra, Deapesh
• Granted Patent: US 8,019,127 B2
• Time in Patent Office: Days
• US Class Current: 715/846
• CPC Class Codes: G06F 21/36 by graphic or iconic representation

Abstract

A system and method for determining if a computer user is a human or a computer program. A computer user is presented with a series of images, the series of images including: at least two related images of an object, at least one of the at least two related images independently processed using an image modifying algorithm; and at least one unrelated image. The computer user is then requested to identify the related images from the series of images. These image identifications are received from the computer user. A determination is made that the computer user is: a human if the image identifications only identify the related images from the series of images; and a non-human if the image identifications do not only identify the related images from the series of images.

Claims

1. A method for determining if a computer user is a human or a computer program, the method comprising:

a) selecting a first image of an individual face from a multitude of face images;

b) selecting a first image filter from a multitude of image modification filters;

c) generating a first modified image by processing the first image using the first image filter;

d) selecting a second image of the individual face from the multitude of face images;

e) selecting a second image filter from the multitude of image modification filters;

f) generating a second modified image by processing the second image using the second image filter;

g) presenting to the computer user a series of images, the series of images including;

i) the first modified image;

ii) the second modified image; and

iii) at least one unrelated image;

h) prompting the computer user to identify the first modified image and second modified image from the series of images;

i) receiving a set of identified images from the computer user;

j) determining that the computer user is;

i) a human if only the first modified image and second modified image from the set of identified images were properly identified by the computer user; and

ii) a non-human if only the first modified image and second modified image from the set of identified images were not properly identified by the computer user.

2. The method for determining if a computer user is a human or a computer program, the method comprising:

a) presenting to the computer user a series of images, the series of images including;

i) at least two related images of an object, at least one of the at least two related images independently processed using an image modifying algorithm; and

ii) at least one unrelated image;

b) prompting the computer user to identify the related images from the series of images;

c) receiving image identifications from the computer user; and

d) determining that the computer user is;

i) a human if the image identifications only identify the related images from the series of images; and

ii) a non-human if the image identifications do not only identify the related images from the series of images.

3. The method according to claim 2, wherein the image modifying algorithm is selected from a multitude of image modifying algorithms.

4. The method according to claim 3, wherein the multitude of image modifying algorithms is stored in a database.

5. The method according to claim 3, wherein the algorithm selection is random.

6. The method according to claim 3, wherein at least one of the multitude of image modifying algorithms is a distortion algorithm.

7. The method according to claim 2, wherein the object is a human face.

8. The method according to claim 2, wherein at least two of the at least two related images are different images of the same object.

9. The method according to claim 2, wherein at least two of the at least two related images are the same image processed by different image modifying algorithms.

10. The method according to claim 2, wherein at least one of the multitude of image modifying algorithms performs no noticeable distortion.

11. The method according to claim 2, wherein at least one of the related images is selected from a database.

12. The method according to claim 2, wherein at least one of the related images is randomly selected from a database.

13. The method according to claim 2, wherein the object is a picture.

14. The method according to claim 13, wherein the picture is obtained from a database of pictures.

15. A system for determining if a computer user is a human or a computer program, the system comprising:

a) an image presentation module configured to present to the computer user a series of images, the series of images including;

i) at least two related images of an object, at least one of the at least two related images independently processed using an image modifying algorithm; and

ii) at least one unrelated image;

b) an identification request module configured to prompt the computer user to identify the related images from the series of images;

c) an identification reception module configured to receive image identifications from the computer user; and

d) a computer user determination module configured to determine that the computer user is;

i) a human if the image identifications only identify the related images from the series of images; and

ii) a non-human if the image identifications do not only identify the related images from the series of images.

16. The system according to claim 15, further including an image selection module configured to select the image modifying algorithm from a multitude of image modifying algorithms.

17. The system according to claim 16, wherein multitude of image modifying algorithms are stored in a database.

18. The system according to claim 16, wherein at least one of the multitude of image modifying algorithms is a distortion algorithm.

19. The system according to claim 16, wherein the object is a human face.

20. The system according to claim 16, wherein at least two of the at least two related images are different images of the same object.

21. The system according to claim 16, wherein at least two of the at least two related images are the same image processed by different image modifying algorithms.

22. The system according to claim 16, wherein at least one of the multitude of image modifying algorithms performs no noticeable distortion.

23. The system according to claim 16, further including an image selection module configured to select at least one of the related images from a database.

24. The system according to claim 16, wherein the:

the image presentation module;

the identification request module;

the identification reception module; and

the computer user determination module are stored on a tangible computer readable medium as a series of processor executable instructions.