IP Library › Granted Patent US 11,461,782
Granted Patent B1
US 11,461,782 · App. 12/457,446 · Granted Oct 4, 2022

Distinguishing humans from computers

Inventor: William Randolph Zettler, Jr. (Seattle, WA)
Assignee: Amazon Technologies, Inc.
G06Q20/409
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,461,782
App. No.
12/457,446
Filed
Jun 11, 2009
Granted
Oct 4, 2022
Kind
B1
Art Unit
3685
USPC
705/51
Abstract

Systems and methods are provided that distinguish humans from computers. In one implementation, a computer-implemented method selects, from a storage device, a plurality of images. The method further generates a document comprising the plurality of images for the security challenge. At least one image included in the plurality of images is oriented for display in a different direction than the other images. The method further receives a selection of one or more images included in the plurality of images and determines whether the selected one or more images is oriented for display in a different direction than the other images.

Claims (41)

1. A computer-implemented method for providing a security challenge, comprising:

selecting, by a computing device, a subset of images from a plurality of images based at least in part on the subset of images including a number of text-like edges that exceed a threshold, where the text-like edges are determined based at least in part on a ratio of rising versus falling edges depicted in images of the plurality of images;

orienting, by the computer device, at least one image of the subset of images in a different direction from other images in the subset of images;

providing, by the computing device, a security challenge comprising the subset of images including at least the number of text-like edges that exceed the threshold;

receiving, by the computing device via a communication network, a selection of one or more of the images included in the subset of images; and

determining, by the computing device, the selection of the one or more of the images in the subset of images is oriented for display in the different direction than the other ones of the images in the subset of images.

2. The computer-implemented method of claim 1 , further comprising determining, by the computing device, the text-like edges included on respective images is of a size and clarity.

3. The computer-implemented method of claim 1 , further comprising determining, by the computing device, the security challenge can include the subset of images based at least in part on metadata associated with respective images of the subset of images.

4. The computer-implemented method of claim 1 , further comprising providing instructions for responding to the security challenge.

5. The computer-implemented method of claim 1 , further comprising:

distorting one or more of the images in the subset of images, the one or more images including different text content from the images in the subset of images; and

including the one or more images in the security challenge.

6. The computer-implemented method of claim 1 , further comprising:

orienting at least one image of the subset of images upside-down, the at least one image including different text content from the subset of images; and

including the at least one of the images in the security challenge.

7. The computer-implemented method of claim 1 , further comprising:

orienting at least one of the images included in the subset of images right-side up, the at least one image including different text content from the subset of images; and

including the at least one image in the security challenge.

8. The computer-implemented method of claim 1 , further comprising determining the plurality of images from images of products that include text.

9. The computer-implemented method of claim 1 , further comprising determining the plurality of images from images of book covers including text.

10. A system for providing a security challenge, the system comprising:

an authentication server that:

obtains a plurality of images;

generates a security challenge comprising a subset of images of the plurality of images comprising a ratio of rising versus falling edges depicted in the subset of images that is above a certain threshold;

orients at least one image included in the security challenge to a different direction than other images in the subset of images;

receives via a communication network a selection received at a user device of one or more of the images included in the security challenge; and

determines the selection of one or more of the images is oriented for display in a different direction than the other images in the subset of images.

11. The system of claim 10 , further comprising a data store that stores metadata indicating whether the plurality of images are appropriate for security challenges.

12. The system of claim 10 , wherein the authentication server orients at least one of the images included in the subset of images upside-down.

13. The system of claim 10 , wherein the authentication server orients at least one of the images included in the subset of images is oriented for display right-side up.

14. The system of claim 10 , wherein the authentication server determines the plurality of images from book covers that include text.

15. A computer-implemented method comprising:

generating a security challenge by at least selecting a subset of images from a set of images based at least in part on a ratio of rising versus falling edges depicted in the subset of images exceeding threshold;

modifying the security challenge by at least causing a first image of the set of images to be rotated by a number of degrees;

providing the security challenge to a computing device via a communication network; and

receiving, from the computing device, a selection of the first image in response to the security challenge.

16. The computer-implemented method of claim 15 , wherein the computer-implemented method further comprises determining that the set of images can be included in the security challenge based on metadata associated with the set of images.

17. The computer-implemented method of claim 15 , wherein rotating the first image by the number of degrees causes text depicted in the first image to be displayed upside down.

18. The computer-implemented method of claim 15 , wherein generating the security challenge further comprises selecting a second image to be included in the security challenge based on a number of edges existing in rows of pixels in the second image.

19. The computer-implemented method of claim 15 , wherein the set of images further comprises images of book covers.

20. The computer-implemented method of claim 15 , wherein generating the security challenge further comprises selecting a second image to be included in the security challenge based at least in part on a variance of rows of pixels in the second image exceeding a second threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 12, 2010
From: ZETTLER, WILLIAM RANDOLPH, JR.
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 024828/0960 →
Cited By (1)
US 12,470,556