Polarized images for security

• US 9,536,362 B2
• Filed: 05/16/2014
• Issued: 01/03/2017
• Est. Priority Date: 09/27/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Sarwar, Mushtaq A., Bilbrey, Brett, Zheng, Peng
• Primary Examiner(s): Czekaj, Dave
• Assistant Examiner(s): HAQUE, MD NAZMUL
• Application Number:
  US14/279,648
• Publication Number:
  US 20140247361A1
• Time in Patent Office: 963 Days
• US Class Current: 1/1
• CPC Class Codes: G01J 4/00 Measuring polarisation of light
• CPC Class Codes: G02B 30/25 using polarisation techniques
• CPC Class Codes: G06T 7/557 from light fields, e.g. from plenoptic cameras
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/596 from three or more stereo images
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: H04N 13/243 using three or more 2D image sensors
• CPC Class Codes: H04N 13/25 using two or more image sensors with different characteristics other than in their location or field of view, e.g. having different resolutions or colour pickup characteristics; using image signals from one sensor to control the characteristics of another sensor
• CPC Class Codes: H04N 13/271 wherein the generated image signals comprise depth maps or disparity maps

Abstract

One embodiment may take the form of a method for providing security for access to a goal including storing a first image and receiving a second image comprising polarized data. The method also includes comparing the first image with the second image to determine if the first image and the second image are substantially the same. In the event the first and second images are not substantially the same, the method includes denying access to the goal. In the event the first and second images are substantially the same, the method includes determining, utilizing the polarized information, if the second image is of a three-dimensional object. Further, in the event the second image is not of a three-dimensional object, the method includes denying access to the goal and, in the event the second image is of a three-dimensional object, permitting access to the goal.

Claims

1. A method for providing facial recognition security, comprising receiving a first image of an individual captured by a polarizing image capture device;

comparing facial metrics in the first image to facial metrics in a second image of the individual to determine if the first and second images are of the same individual;

if the first and second images are of the same individual, determining if the first image is of a three-dimensional object based on polarized data in the image;

if the first image is of a three-dimensional object, comparing the first image with one or more other images of the individual captured by the polarizing image capture device to determine if a micro-movement indicative of a human occurred between the first image and at least one of the one or more other images; and

if a micro-movement indicative of a human occurred between the first and at least one of the one or more other images, providing a positive result to the individual.

2. The method as in claim 1, wherein the positive result comprises granting access to the individual.

3. The method as in claim 1, further comprising denying access to the individual if a micro-movement indicative of a human did not occur between the first and the one or more other images.

4. The method as in claim 1, further comprising denying access to the individual if the first image is not of a three-dimensional object.

5. The method as in claim 1, further comprising denying access to the individual if the first and second images are not of the same individual.

6. The method as in claim 5, further comprising generating an alert when the first and second images are not of the same individual.

7. The method as in claim 1, further comprising:

if the first and second images are not of the same individual, searching a database of images of individuals to determine if the first image corresponds to another image in the database; and

if the first image does not match any images in the database of images, denying access to the individual.

8. The method as in claim 1, wherein the second image is one of the one or more other images captured by the polarizing image capture device.

9. The method as in claim 1, wherein determining if the first image is of a three-dimensional object based on the polarized data comprises computing at least one of a degree of linear polarization, an angle of polarization, and a surface normal.

10. The method as in claim 9, further comprising computing stokes parameters to compute at least one of the degree of linear polarization, the angle of polarization, and the surface normal.

11. The method as in claim 1, wherein the one or more micro-movements indicative of a human comprises at least one of:

a respiratory movement;

a movement induced by a pulse rate; and

an eye movement;

a movement of the head;

a movement of the lips; and

a movement of clothing worn by the individual.

12. A security system comprising:

a camera comprising a photosensor and a polarizer, the camera capturing images of an individual;

a processor coupled to the camera; and

a storage device coupled to the processor and operative to store one or more images of an individual;

wherein the processor is configured to compare at least one captured image of the individual with the one or more stored images to determine if the at least one captured image and the one or more stored images are of the same individual;

wherein the processor is configured to determine if at least one captured image is of a three-dimensional object based on polarized data in the image,

wherein the processor is configured to determine if one or more micro-movements indicative of a human occurred between the captured images; and

wherein the processor is further configured to grant access to the individual if at least one captured image and at least one stored image are of the same individual, if at least one image of the individual captured by the camera is of a three-dimensional object, and if one or more micro-movements indicative of a human occurred between the images.

13. The security system as in claim 12, wherein the processor is further configured to deny access to the individual if at least one image of the individual captured by the camera is of a three-dimensional object.

14. The security system as in claim 12, wherein the processor is further configured to deny access to the individual if one or more micro-movements indicative of a human did not occur between the images.

15. The security system as in claim 12, wherein the processor is further configured to generate an alert and deny access to the individual if individual in the captured images does not match at least one individual in the stored images.

16. The security system as in claim 12, wherein the processor is configured to compute at least one of a degree of linear polarization, an angle of polarization and a surface normal for the captured image when determining if at least one image of the individual captured by the camera is of a three-dimensional object.

17. The security system as in claim 12, wherein the polarizer comprises a linear polarizer divided into four blocks with the blocks having polarization angles of 0, 45, 90, and −

45 degrees.

18. The security system as in claim 17, wherein the linear polarizer is integrated into a Bayer layer.

19. The security system as in claim 17, wherein a Bayer layer is disposed between the photosensor and the linear polarizer and each block of the linear polarizer corresponds to a distinct pixel of each captured image and to a particular color block of the Bayer layer.

20. The security system as in claim 12, wherein the polarizer has a single polarizing axis and the polarizer is configured to rotate to capture multiple images at different polarization angles.