Liveness detection

• US 10,305,908 B2
• Filed: 09/15/2017
• Issued: 05/28/2019
• Est. Priority Date: 08/10/2015
• Status: Active Grant

• Current Assignee: Yoti Holding Ltd
• Original Assignee: Yoti Holding Ltd
• Inventors: Paraskevas, Georgios, Rodriguez, Francisco Angel Garcia, Khan, Usman Mahmood, Tremoulheac, Benjamin Robert
• Primary Examiner(s): Bayou, Yonas A
• Application Number:
  US15/706,461
• Publication Number:
  US 20180083973A1
• Time in Patent Office: 620 Days
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• 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 40/193 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: G06V 40/67 by interactive indications to the user
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources

Abstract

In a liveness detection system, a first set of one or more parameters of a first liveness test is selected at random. The first parameter set is transmitted to a user device available to an entity, thereby causing the user device to perform the first liveness test according to the first parameter set. Results of the first liveness test performed at the user device according to the first parameter set are received form the user device. Results of a second liveness test pertaining to the entity are received. The liveness detection system determines whether the entity is a living being using the results of the liveness tests, the results of the first liveness test being so used by comparing them with the first parameter set.

Claims

1. A liveness detection system comprising:

a video input configured to receive a moving image of an entity captured by a camera over an interval of time; and

one or more hardware processors configured to;

control a display to display, to the entity over the interval of time, at least one randomly selected word at a random location of the display;

process the moving image to detect an eye and a mouth of the entity;

compare;

(i) movement of the mouth exhibited over the interval of time with the randomly selected word using a lip reading algorithm, to determine whether the mouth is speaking the randomly selected word in the moving image, and

(ii) movement of the eye exhibited over the interval of time with the random location of the randomly selected word, to determine whether the eye exhibits an expected movement in the moving image, to thereby determine whether the entity is a living being; and

grant or refuse an access request for the entity, the access request relating to a computer system, based on said determination as to whether the entity is a living being.

2. The liveness detection system according to claim 1 wherein the one or more hardware processors are further configured to:

identify, for each of a plurality of frames of the moving image, an iris area, the iris area corresponding to the iris of the eye in the frame;

generate, for each of a plurality of regions of the iris area, a histogram of pixel values within that region for use in tracking movements of the eye; and

wherein the one or more hardware processors are configured to perform said comparison by comparing the histograms with the expected movement.

3. The liveness detection system according to claim 2, wherein the liveness detection module is configured to perform said comparison by comparing the histograms with a probability density function representing the expected movement.

4. The liveness detection system according to claim 2, comprising:

a spatial windowing module configured, for each of a plurality of frames of the moving image, to divide at least a portion of that frame into a plurality of blocks, each block formed one or more respective sub-blocks, each sub-block formed of one or more respective pixels; and

an analysis module configured to assign to each block a respective block value based on its one or more respective sub-blocks, the liveness detection module being configured to perform said comparison by comparing the block values with the expected movement.

5. The liveness detection system according to claim 4, wherein each sub-block is formed of a multiple pixels, and/or each block is formed of multiple sub-blocks.

6. The liveness detection system according to claim 4, wherein the analysis module is configured to assign to each sub-block a binary value by detecting whether or not at least a predetermined proportion of its respective pixels have intensities below an intensity threshold, the block value of each block being assigned by combining the binary values assigned to its respective sub-blocks.

7. The liveness detection system according to claim 6, wherein the pixel intensities are determined by converting the plurality of frames from a color format into a grayscale format.

8. The liveness detection system according to claim 1, wherein the one or more hardware processors are configured to grant the entity access to a remote computer system only if they are determined to be a living being.

9. The liveness detection system according to claim 1 wherein the liveness detection module is configured to output at least one of:

a confidence value which conveys a probability that the entity is a living being, and a binary classification of the entity as either living or non-living.

10. A computer-implemented liveness detection method comprising:

controlling a display to display, to an entity over an interval of time, at least one randomly selected word at a random location of the display;

receiving a moving image of the entity captured by a camera over the interval of time;

processing the moving image to detect an eye and a mouth of the entity;

comparing;

(i) movement of the mouth exhibited over the interval of time with the randomly selected word using a lip reading algorithm, to determine whether the mouth is speaking the randomly selected word in the moving image, and

(ii) movement of the eye exhibited over the interval of time with the random location of the randomly selected word, to determine whether the eye exhibits an expected movement in the moving image,

to thereby determine whether the entity is a living being; and

granting or refusing an access request for the entity, the access request relating to a computer system, based on said determination as to whether the entity is a living being.

11. Non-transitory computer-readable media comprising computer readable instructions that, when executed by a computing system, cause the computing system to implement a method comprising:

controlling a display, to display to an entity over an interval of time, at least one randomly selected word at a random location of the display;

receiving a moving image of the entity captured by a camera over the interval of time;

processing the moving image to detect an eye and a mouth of the entity;

comparing;

(i) movement of the mouth exhibited over the interval of time with the randomly selected word using a lip reading algorithm, to determine whether the mouth is speaking the randomly selected word in the moving image, and

(ii) movement of the eye exhibited over the interval of time with the random location of the randomly selected word, to determine whether the eye exhibits an expected movement in the moving image,

to thereby determine whether the entity is a living being; and

granting or refusing an access request for the entity, the access request relating to a computer system, based on said determination as to whether the entity is a living being.