Method and a device for detecting fraud by examination using two different focal lengths during automatic face recognition
A method and an associated device for detecting fraud during automatic face recognition, the method comprising the following steps: acquiring a first image of the face by means of a first sensor having a first field angle, and a second image of the face by means of a second sensor having a second field angle that is narrower than the first field angle; analyzing the first image to verify that there is no frame around the face; and analyzing the second image to verify that there is no moiré effect.
1. An automatic face recognition method, the method comprising a fraud detection stage including the following steps:
acquiring at least one first image of the face by means of a first sensor having a first field angle;
substantially simultaneously, acquiring at least one second image of the face by means of a second sensor having a second field angle, the sensors having fields of view covering a common zone in three-dimensional space, and the first field angle being wider than the second field angle;
analyzing the first image only to detect border around the face;
analyzing the second image to verify that there is no moiré effect;
detecting the absence of fraud when there is no border detected in the first image and no moiré effect detected in the second image; and
a positioning stage for positioning a candidate to face the second sensor, the positioning stage comprising the steps of capturing at least one image by means of the first sensor, of detecting a position of the candidate's face in said image, and of selecting at least one positioning indication in function of the detected position to be provided to the candidate in order to cause the candidate to position his/her face in the field of view of the second sensor.
2. The method according to claim 1 , wherein the method further comprising a recognition stage that performs recognition by analyzing the second image.
3. An image capture device, comprising a control unit connected both to a first image sensor having a first field angle and also to a second image sensor having a second field angle, the sensors being pointed to have fields of view covering a common zone in three-dimensional space and the first field angle being wider than the second field angle, the control unit being arranged to implement a method comprising, during a fraud detection stage, the following steps:
acquiring at least one first image of the face by means of a first sensor having a first field angle;
substantially simultaneously, acquiring at least one second image of the face by means of a second sensor having a second field angle, the sensors having fields of view covering a common zone in three-dimensional space, and the first field angle being wider than the second field angle;
analyzing the first image only to detect border around the face;
analyzing the second image to verify that there is no moiré effect; and
detecting the absence of fraud when there is no border detected in the first image and no moiré effect detected in the second image;
wherein the image capture device further comprises an assistance system for assisting with positioning the face in front of the second sensor by using the first sensor.
4. The device according to claim 3 , wherein acquisition and analysis are performed on a plurality of images from a video recording.
5. The device according to claim 3 , wherein the second image sensor has an image resolution that is specifically adapted to enable a moiré effect to be detected when the face is too close to the first sensor to enable the first image sensor to capture the outline of the face.
6. The device of claim 3 , further comprising a communication unit.
7. The device according to claim 3 , wherein the method further comprises a recognition stage that performs recognition by analyzing the second image.
8. An image capture device, comprising a control unit connected both to a first image sensor having a first field angle and also to a second image sensor having a second field angle, the sensors being pointed to have fields of view covering a common zone in three-dimensional space and the first field angle being wider than the second field angle, the control unit being arranged to implement a method comprising a fraud detection stage that includes the following steps:
acquiring at least one first image of the face by means of a first sensor having a first field angle;
substantially simultaneously, acquiring at least one second image of the face by means of a second sensor having a second field angle, the sensors having fields of view covering a common zone in three-dimensional space, and the first field angle being wider than the second field angle;
analyzing the first image only to detect border around the face; analyzing the second image to verify that there is no moiré effect;
detecting the absence of fraud when there is no border detected in the first image and no moiré effect detected in the second image; and
a positioning stage for positioning a candidate to face the second sensor, the positioning stage comprising the steps of capturing at least one image by means of the first sensor, of detecting a position of the candidate's face in said image, and of selecting at least one positioning indication in function of the detected position to be provided to the candidate in order to cause the candidate to position his/her face in the field of view of the second sensor.
9. The device according to claim 8 , including an assistance system for assisting with positioning the face in front of the second sensor by using the first sensor.
10. The device according to claim 8 , wherein the second image sensor has an image resolution that is specifically adapted to enable a moiré effect to be detected when the face is too close to the first sensor to enable the first image sensor to capture the outline of the face.
11. The device of claim 8 , further comprising a communication unit.