Liveness detection method, liveness detection system, and computer program product

1. A liveness detection method, comprising:

irradiating an object to be detected with structured light;

obtaining first facial image data of the object to be detected under irradiation of the structured light;

determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected; and

determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body,

wherein the detection parameter is a ratio of a sum of gradient magnitudes of the first facial image data within a predetermined region to a total brightness value of the image within the predetermined region, or

wherein determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected comprises:

dividing the first facial image data into a plurality of sub-image regions;

performing Fourier transform on sub-image data of each sub-image region to obtain a sub-image Fourier transform coefficient of each sub-image region;

as for each sub-image region, calculating a ratio of a sum of squares of the sub-image Fourier transform coefficient within a predetermined frequency range to a square of a sub-image Fourier transform lowest frequency coefficient; and

calculating an average of the ratios in the plurality of sub-image regions as the detection parameter.

2. The liveness detection method according to claim 1 , further comprising:

prior to irradiating an object to be detected with structured light, continuously capturing a monitoring image of the object to be detected;

detecting, by a face detecting unit that is trained in advance, the monitoring image to obtain a monitoring result;

when the monitoring result indicates that there is a facial image in the monitoring image, turning on a structured light source to emit the structured light for irradiating the object to be detected.

3. The liveness detection method according to claim 1 , wherein when the detection parameter is the ratio of the sum of gradient magnitudes of the first facial image data within the predetermined region to the total brightness value of the image within the predetermined region, the method further comprises:

determining a plurality of predetermined facial key points on the first facial image data by a facial key point detecting unit that is trained in advance, and determining the predetermined region according to the plurality of predetermined facial key points.

4. The liveness detection method according to claim 1 , wherein determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body comprises:

if the detection parameter is larger than a first parameter threshold and smaller than a second parameter threshold, determining that the object to be detected passes the liveness detection;

otherwise, determining that the object to be detected fails the liveness detection.

5. A liveness detection system, comprising:

a structured light source module for emitting structured light to irradiate an object to be detected;

an image data obtaining module for obtaining first facial image data of the object to be detected under irradiation of the structured light; and

a liveness detecting module for determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected, and determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body,

wherein the detection parameter is a ratio of a sum of gradient magnitudes of the first facial image data within a predetermined region to a total brightness value of the image within the predetermined region, or

wherein the liveness detecting module divides the first facial image data into a plurality of sub-image regions; performs Fourier transform on sub-image data of each sub-image region to obtain a sub-image Fourier transform coefficient of each sub-image region; as for each sub-image region, calculates a ratio of a sum of squares of the sub-image Fourier transform coefficient within a predetermined frequency range to a square of a sub-image Fourier transform lowest frequency coefficient and calculates an average of the ratios in the plurality of sub-image regions as the detection parameter.

6. The liveness detection system according to claim 5 , wherein prior to the structured light source module emits structured light to irradiate an object to be detected, the image data obtaining module continuously captures a monitoring image of the object to be detected;

the liveness detecting module detects, by a face detecting unit that is trained in advance, the monitoring image to obtain a monitoring result;

when the monitoring result indicates that there is a facial image in the monitoring image, the liveness detecting module turns on the structured light source module to emit the structured light for irradiating the object to be detected.

7. The liveness detection system according to claim 5 , wherein when the detection parameter is the ratio of the sum of gradient magnitudes of the first facial image data within the predetermined region to the total brightness value of the image within the predetermined region, the liveness detecting module determines, by a facial key point detecting unit that is trained in advance, a plurality of predetermined facial key points on the first facial image data, and determines the predetermined region according to the plurality of predetermined facial key points.

8. The liveness detection system according to claim 5 , wherein if the detection parameter is larger than a first parameter threshold and smaller than a second parameter threshold, the liveness detecting module determines that the object to be detected passes the liveness detection;

otherwise, the liveness detecting module determines that the object to be detected fails the liveness detection.

9. A liveness detection device, comprising:

a processor;

a memory; and

computer program instructions stored in the memory and when run by the processor, configured to cause the liveness detection device to perform a liveness detection method comprising the following steps:

irradiating an object to be detected with structured light;

obtaining first facial image data of the object to be detected under irradiation of the structured light;

determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected; and

determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body,

wherein the detection parameter is a ratio of a sum of gradient magnitudes of the first facial image data within a predetermined region to a total brightness value of the image within the predetermined region, or

wherein the step of determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected performed by the liveness detection device caused by the computer program instructions run by the processor comprises:

dividing the first facial image data into a plurality of sub-image regions;

performing Fourier transform on sub-image data of each sub-image region to obtain a sub-image Fourier transform coefficient of each sub-image region;

as for each sub-image region, calculating a ratio of a sum of squares the sub-image Fourier transform coefficient within a predetermined frequency range to a square of a sub-image Fourier transform lowest frequency coefficient; and

calculating an average of the ratios in the plurality of sub-image regions as the detection parameter.

10. The liveness detection device as claimed in claim 9 , wherein when the computer program instructions are run by the processor, the liveness detection device is caused to perform the step of:

prior to irradiating an object to be detected with structured light, continuously capturing a monitoring image of the object to be detected;

detecting, by a face detecting unit that is trained in advance, the monitoring image to obtain a monitoring result;

when the monitoring result indicates that there is a facial image in the monitoring image, turning on a structured light source to emit the structured light for irradiating the object to be detected.

11. The liveness detection device as claimed in claim 9 , wherein when the detection parameter is the ratio of the sum of gradient magnitudes of the first facial image data within the predetermined region to the total brightness value of the image within the predetermined region, and when the computer program instructions are run by the processor, the liveness detection device is caused to perform the step of:

determining a plurality of predetermined facial key points on the first facial image data by a facial key point detecting unit that is trained in advance and determining the predetermined region according to the plurality of predetermined facial key points.

12. The liveness detection device according to claim 9 , wherein the step of determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body performed by the liveness detection device caused by the computer program instructions run by the processor comprises:

if the detection parameter is larger than a first parameter threshold and smaller than a second parameter threshold, determining that the object to be detected passes the liveness detection;

otherwise, determining that the object to be detected fails the liveness detection.