Fraud detection for facial recognition systems

• US 9,230,158 B1
• Filed: 12/18/2012
• Issued: 01/05/2016
• Est. Priority Date: 12/18/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Ramaswamy, Sharadh
• Primary Examiner(s): Chawan, Sheela C
• Application Number:
  US13/718,649
• Time in Patent Office: 1,113 Days
• Field of Search: 382/118, 382/115, 382/154, 382/209, 382/190, 382/159, 348/143, 348/E5.024, 348/222.1, 348/207.99, 345/419, 704/275, 704/246, 704/270, 704/E17.003, 704/231, 704/273, 726/19, 726/17, 726/2, 726/16, 707/769
• US Class Current: 1/1
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

Approaches are described which enable a computing device (e.g., mobile phone, tablet computer) to utilize one or more facial recognition techniques to control access to the device and to detect when artificial representations of a user, such as a picture or photograph, are being used in an attempt to gain access to the device. Evidence indicative of artificial representations may include lack of changes in facial skin color between multiple images captured by a camera, ability to track one or more features of the human face while the camera is rotated or moved, presence of secular reflections caused by an illumination device, absence of shadows in the image, and others.

Claims

1. A computer implemented method, comprising:

under control of one or more computer systems configured with executable instructions,

capturing a first image using a camera, the first image including first image data corresponding to at least one portion of a human face taken at a first angle relative to the camera;

analyzing the first image data to identify the at least one portion of the human face;

capturing a second image using the camera, the second image including second image data corresponding to the at least one portion of the human face taken at a second angle relative to the camera;

analyzing the first image data and the second image data to detect changes in one or more characteristics corresponding to the at least one portion of the human face;

determining, based at least in part on the changes in the one or more characteristics, that an artificial representation of the at least one portion of the human face is presented in the first image and the second image; and

preventing access to at least one function of a computing device.

2. The computer implemented method of claim 1, wherein the changes in the one or more characteristics comprises:

one or more changes in facial skin color for the at least one portion of the human face between the first image data and the second image data.

3. The computer implemented method of claim 1, wherein the changes in the one or more characteristics comprises:

one or more changes in shadows for the at least one portion of the human face between the first image data and the second image data.

4. The computer implemented method of claim 1, wherein detecting the changes in the one or more characteristics further comprises:

detecting, one or more specular reflections for the at least one portion of the human face in the first image data and the second image data, the specular reflection caused by light produced by an illumination device, wherein the one or more specular reflections indicate a flat surface on which a two dimensional representation of the portion of the human face is rendered.

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

presenting instructions to a user of the computing device to rotate or move the computing device from the first angle relative to the camera to the second angle relative to the camera.

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

capturing a third image using the camera, the third image including third image data corresponding to the at least one portion of the human face taken under light produced by an illumination device;

analyzing the third image data to detect a presence of red-eye effect in the third image data; and

providing the access to the at least one function of the computing device.

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

comparing the at least one portion of the human face in the first image data and the second image data to a stored model of a face of an authorized user of the computing device.

8. A computing device, comprising:

a camera;

at least one processor; and

memory including instructions that, when executed by the at least one processor, cause the computing device to;

capture a first image using the camera, the first image including first image data corresponding to at least one portion of a human face taken at a first angle relative to the camera;

capture a second image using the camera, the second image including second image data corresponding to the at least one portion of the human face taken at a second angle relative to the camera;

analyze the first image data and the second image to detect changes in one or more characteristics corresponding to the at least one portion of the human face;

determine, based at least in part on the changes in the one or more characteristics, that an artificial representation of the at least one portion of the human face is presented in the first image and the second image; and

prevent access to at least one function of the computing device.

9. The computing device of claim 8, wherein the changes in the one or more characteristics comprises:

one or more changes in facial skin color for the at least one portion of the human face between the first image data and the second image data.

10. The computing device of claim 8, wherein the changes in the one or more characteristics comprises:

one or more changes in shadows for the at least one portion of the human face between the first image data and the second image data.

11. The computing device of claim 8, wherein detecting the changes in the one or more characteristics further comprises:

detecting one or more specular reflections for the at least one portion of the human face in the first image data and the second image data, the specular reflection caused by light produced by an illumination device, wherein the one or more specular reflections indicate a flat surface on which a two dimensional representation of the portion of the human face is rendered.

12. The computing device of claim 8, wherein the memory further includes instructions that, when executed by the at least one processor, cause the computing device to:

present instructions to a user of the computing device to rotate the computing device from the first angle relative to the camera to the second dangle relative to the camera.

13. The computing device of claim 8, wherein the memory further includes instructions that, when executed by the at least one processor, cause the computing device to:

capture a third image using the camera, the third image including third image data corresponding to the at least one portion of the human face taken under light produced by an illumination device;

analyze the third image data to detect a presence of red-eye effect in the third image data; and

provide the access to the at least one function of the computing device.

14. The computing device of claim 8, wherein the memory further includes instructions that, when executed by the at least one processor, cause the computing device to:

compare the at least one portion of the human face in the first image data and the second image data to a stored model of a face of an authorized user of the computing device.

15. A non-transitory computer readable storage medium storing one or more sequences of instructions executable by one or more processors to perform a set of operations comprising:

capturing a first image using a camera, the first image including first image data corresponding to at least one portion of a human face taken at a first angle relative to the camera;

capturing a second image using the camera, the second image including second image data corresponding to the at least one portion of the human face taken at a second angle relative to the camera;

analyzing the first image data and the second image to detect changes in one or more characteristics corresponding to the at least one portion of the human face;

determining, based at least in part on the changes in the one or more characteristics, that an artificial representation of the at least one portion of the human face is presented in the first image and the second image; and

preventing access to at least one function of a computing device.

16. The non-transitory computer readable storage medium of claim 15, wherein the changes in the one or more characteristics comprises:

one or more changes in facial skin color for the at least one portion of the human face between the first image data and the second image data.

17. The non-transitory computer readable storage medium of claim 15, wherein the changes in the one or more characteristics comprises:

one or more changes in shadows for the at least one portion of the human face between the first image data and the second image data.

18. The non-transitory computer readable storage medium of claim 15, further storing instructions executable by the one or more processors to perform operations of:

detecting one or more specular reflections for the at least one portion of the human face in the first image data and the second image data, the specular reflection caused by light produced by an illumination device, wherein the one or more specular reflections indicate a flat surface on which a two dimensional representation of the portion of the human face is rendered.

19. The non-transitory computer readable storage medium of claim 15, further storing instructions executable by the one or more processors to perform operations of:

presenting instructions to a user of the computing device to rotate the computing device from the first angle relative to the camera to the second dangle relative to the camera.

20. The non-transitory computer readable storage medium of claim 15, further storing instructions executable by the one or more processors to perform operations of:

capturing a third image using the camera, the third image including third image data corresponding to the at least one portion of the human face taken under light produced by an illumination device;

analyzing the third image data to detect a presence of red-eye effect in the third image data; and

providing the access to the at least one function of the computing device.