System and method for liveness detection

Patent metadata

Field	Value
Publication number	US-11093770-B2
Application number	US-201816236917-A
Country	US
Kind code	B2
Filing date	Dec 31, 2018
Priority date	Dec 29, 2017
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for liveness detection are disclosed. In one aspect, a method includes the actions of capturing video data that includes multiple video frames that each include a representation of a face of a user while activating multiple light sources according to a predetermined lighting pattern. The actions further include, for each of the multiple video frames that each include the representation of the face of the user, analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame. The actions further include, based on analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern, determining whether the face of the user is that of a live person or a static image.

First claim

What is claimed is:

1. A computer-implemented method comprising:
capturing, by a computing device, video data that includes multiple video frames that each include a representation of a face of a user while activating multiple light sources according to a predetermined lighting pattern;
for each of the multiple video frames that each include the representation of the face of the user, analyzing, by the computing device, the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame, wherein analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame comprises analyzing shadow patterns on each of the respective video frames; and
based on analyzing, for each of the multiple video frames, the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame, determining, by the computing device, whether the face of the user is that of a live person or a static image, wherein determining whether the face of the user is that of a live person or a static image is based on the shadow patterns on each of the respective video frames.

2. The method of claim 1 , comprising:
based on analyzing shadow patterns on each of the respective video frames, determining that the representation of the face of the user includes shadow patterns that indicate three-dimensional facial features on the representation of the face of the user,
wherein determining whether the face of the user is that of a live person or a static image comprises determining that the face of the user is that of a live person based on determining that the representation of the face of the user includes shadow patterns that indicate three-dimensional facial features on the representation of the face of the user.

3. The method of claim 1 , comprising:
based on analyzing shadow patterns on each of the respective video frames, determining that the representation of the face of the user includes shadow patterns that indicate two-dimensional facial features on the representation of the face of the user,
wherein determining whether the face of the user is that of a live person or a static image comprises determining that the face of the user is that of a static image based on determining that the representation of the face of the user includes shadow patterns that indicate two-dimensional facial features on the representation of the face of the user.

4. The method of claim 1 , wherein:
the computing device is a mobile phone,
the video data is captured by a front facing camera of the mobile phone, and
the multiple light sources include multiple LEDs of the mobile phone.

5. The method of claim 1 , wherein:
determining whether the face of the user is that of a live person or a static image is inconclusive, and
the method comprises:
based on determining whether the face of the user is that of a live person or a static image is inconclusive, capturing, by the computing device, additional video data while activating the multiple light sources according to a different lighting pattern.

6. The method of claim 1 , wherein the predetermined lighting pattern comprises a period of time when each of the multiple light sources are off.

7. The method of claim 1 wherein analyzing, by the computing device, the representation of the face of the user includes analyzing based on a portion of the captured video.

8. A system comprising:
one or more computers; and
one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
capturing, by a computing device, video data that includes multiple video frames that each include a representation of a face of a user while activating multiple light sources according to a predetermined lighting pattern;
for each of the multiple video frames that each include the representation of the face of the user, analyzing, by the computing device, the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame wherein analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame comprises analyzing shadow patterns on each of the respective video frames; and
based on analyzing, for each of the multiple video frames, the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame, determining, by the computing device, whether the face of the user is that of a live person or a static image, wherein determining whether the face of the user is that of a live person or a static image is based on the shadow patterns on each of the respective video frames.

9. The system of claim 8 , wherein the operations comprise:
based on analyzing shadow patterns on each of the respective video frames, determining that the representation of the face of the user includes shadow patterns that indicate three-dimensional facial features on the representation of the face of the user,
wherein determining whether the face of the user is that of a live person or a static image comprises determining that the face of the user is that of a live person based on determining that the representation of the face of the user includes shadow patterns that indicate three-dimensional facial features on the representation of the face of the user.

10. The system of claim 8 , wherein the operations comprise:
based on analyzing shadow patterns on each of the respective video frames, determining that the representation of the face of the user includes shadow patterns that indicate two-dimensional facial features on the representation of the face of the user,
wherein determining whether the face of the user is that of a live person or a static image comprises determining that the face of the user is that of a static image based on determining that the representation of the face of the user includes shadow patterns that indicate two-dimensional facial features on the representation of the face of the user.

11. The system of claim 8 , wherein:
the computing device is a mobile phone,
the video data is captured by a front facing camera of the mobile phone, and
the multiple light sources include multiple LEDs of the mobile phone.

12. The system of claim 8 , wherein:
determining whether the face of the user is that of a live person or a static image is inconclusive, and
the method comprises:
based on determining whether the face of the user is that of a live person or a static image is inconclusive, capturing, by the computing device, additional video data while activating the multiple light sources according to a different lighting pattern.

13. The system of claim 8 , wherein the predetermined lighting pattern comprises a period of time when each of the multiple light sources are off.

14. The system of claim 8 wherein analyzing, by the computing device, the representation of the face of the user includes analyzing based on a portion of the captured video.

15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon suc

Assignees

• Idemia Identity & Security USA LLC

Inventors

• Miu Stephen
• Wu Yecheng

Classifications

• G06Q20/40145 Primary

  Biometric identity checks · CPC title

• G06V40/45 Primary

  Detection of the body part being alive · CPC title

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06V40/168

  Feature extraction; Face representation · CPC title