Spoof detection using iris images

Patent metadata

Field	Value
Publication number	US-11023756-B2
Application number	US-201816172546-A
Country	US
Kind code	B2
Filing date	Oct 26, 2018
Priority date	Oct 26, 2018
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

The technology described in this document can be embodied in a method for preventing access to a secure system based on determining a captured image to be of an alternative representation of a live person. The method includes capturing an image of a subject illuminated by an infrared (IR) illumination source, and extracting, from the image, a portion representative of an iris of the subject. The method also includes determining that an amount of high-frequency features in the portion of the image satisfies a threshold condition indicative of the image being of an alternative representation of a live person, and in response, identifying the subject in the image to be an alternative representation of a live person. Responsive to identifying the subject in the image to be an alternative representation of a live person, the method further includes preventing access to the secure system.

First claim

What is claimed is:

1. A method for preventing access to a secure system based on determining a captured image to be of an alternative representation of a live person, the method comprising:
performing a comparison between frequency domain representations of images of live persons and frequency domain representations of images of alternative representations of live persons;
determining, based on the comparison, a threshold amount of high-frequency features associated with images of live persons;
capturing an image of a subject illuminated by an infrared (IR) illumination source;
extracting, from the image, a portion of the image representative of an iris of the subject;
generating, from the portion of the image representative of the iris of the subject, a frequency domain representation;
determining, based on the frequency domain representation, that an amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons;
responsive to determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons, identifying the subject in the image to be an alternative representation of a live person; and
responsive to identifying the subject in the image to be the alternative representation of the live person, preventing access to the secure system.

2. The method of claim 1 , wherein determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount comprises:
determining that an amount of energy in a high frequency region of the frequency domain representation is less than a threshold amount of energy associated with images of live persons.

3. The method of claim 1 , wherein the alternative representation of the live person comprises a photograph of the live person.

4. The method of claim 3 , wherein the photograph is printed on paper.

5. The method of claim 3 , wherein the photograph is presented on a display device.

6. The method of claim 1 , wherein determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons comprises processing the image using a machine learning process trained to discriminate between images of live persons and alternative representations of live persons.

7. The method of claim 1 , wherein the frequency domain representation comprises a two-dimensional Fast Fourier Transform (2D-FFT) of the portion of the image.

8. The method of claim 1 , further comprising:
determining, based on the frequency domain representation, that the amount of high-frequency features in the portion of the image representative of the iris of the subject is equal to or greater than the threshold amount associated with images of live persons;
responsive to determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is equal to or greater than the threshold amount associated with images of live persons, identifying the subject in the image to be the live person; and
responsive to identifying the subject in the image to be the live person, initiating an authentication process for determining if the live person is authorized to access the secure system.

9. The method of claim 1 , wherein the secure system comprises a user-interface disposed in a kiosk.

10. The method of claim 9 , wherein the IR illumination source is disposed on the kiosk.

11. The method of claim 1 , wherein performing the comparison comprises training a machine learning model to discriminate between the frequency domain representations of images of live persons and the frequency domain representations of images of alternative representations of live persons.

12. A system comprising:
an image acquisition device configured to capture an image of a subject illuminated by an infrared (IR) illumination source; and
an image analysis engine comprising one or more processing devices, the image analysis engine configured to:
perform a comparison between frequency domain representations of images of live persons and frequency domain representations of images of alternative representations of live persons,
determine, based on the comparison, a threshold amount of high-frequency features associated with images of live persons,
extract, from the image, a portion of the image representative of an iris of the subject,
generate, from the portion of the image representative of the iris of the subject, a frequency domain representation,
determine, based on the frequency domain representation, that an amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons,
responsive to determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons, identify the subject in the image to be an alternative representation of a live person, and

responsive to identifying the subject in the image to be the alternative representation of the live person, prevent access to a secure system.

13. The system of claim 12 , wherein the frequency domain representation comprises a two-dimensional Fast Fourier Transform (2D-FFT) of the portion of the image.

14. The system of claim 12 , wherein determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount comprises:
determine that an amount of energy in a high frequency region of the frequency domain representation is less than a threshold amount of energy associated with images of live persons.

15. The system of claim 12 , wherein the alternative representation of the live person comprises a photograph of the live person.

16. The system of claim 15 , wherein the photograph is printed on paper, or presented on a display device.

17. The system of claim 12 , wherein determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is less than the threshold amount associated with images of live persons comprises processing the image using a machine learning process trained to discriminate between images of live persons and alternative representations of live persons.

18. The system of claim 12 , wherein the image analysis engine is configured to:
determine, based on the frequency domain representation, that the amount of high-frequency features in the portion of the image representative of the iris of the subject is equal to or greater than the threshold amount associated with images of live persons;
responsive to determining that the amount of high-frequency features in the portion of the image representative of the iris of the subject is equal to or greater than the threshold amount associated with images of live persons, identify the subject in the image to be the live person; and
responsive to identifying the subject in the image to be the live person, initiate an authentication process for determining if the live person is authorized to access the secure system.

19. The system of claim 12 , wherein the secure system comprises a user-

Assignees

• Advanced New Technologies Co Ltd

Inventors

• Joshi Yash
• Parupati Srikanth

Classifications

• H04N23/20

  for generating image signals from infrared radiation only · CPC title

• G06V40/45 Primary

  Detection of the body part being alive · CPC title

• G06V40/18 Primary

  Eye characteristics, e.g. of the iris · CPC title

• G06V40/40

  Spoof detection, e.g. liveness detection · CPC title

• G06V40/19

  Sensors therefor · CPC title