Spoofing detection device, spoofing detection method, and recording medium
To provide a technology of more accurately detecting spoofing in face authentication, without increasing a scale of a device configuration and a burden on a user. A spoofing detection device includes a facial image sequence acquisition unit, a line-of-sight change detection unit, a presentation information display unit, and a spoofing determination unit. The facial image sequence acquisition unit acquires a facial image sequence indicating the face of a user. The line-of-sight change detection unit detects information about a temporal change in the line-of-sight from the facial image sequence. The presentation information display unit displays presentation information presented to the user as part of an authentication process. The spoofing determination unit determines the likelihood of the face indicated by the facial image sequence being spoofing on the basis of the information about the temporal change in the line-of-sight with respect to the presentation information.
1. A spoofing detection device comprising:
one or more processors configured to:
acquire a facial image sequence indicating a user's face;
detect information about temporal line-of-sight change from the facial image sequence;
display presentation information presented to the user as part of authentication processing while switching the presentation information;
obtain a first temporal change of a value obtained by differentiating a position of the line-of-sight with respect to time;
determine a likelihood that a face indicated by the facial image sequence is spoofing, based on the information about temporal line-of-sight change with respect to the presentation information and a timing of the switching; and
use the first temporal change of the value as the information about temporal line-of-sight change for the determination.
2. The spoofing detection device according to claim 1 , wherein the one or more processors are further configured to:
use a change in a display position of the presentation information by the switching in addition to the information about temporal line-of-sight change and a timing of the switching for the determination.
3. The spoofing detection device according to claim 2 , wherein the one or more processors are further configured to:
use a content of the presentation information in addition to the information about temporal line-of-sight change and a timing of the switching for the determination.
4. The spoofing detection device according to claim 1 , wherein the one or more processors are further configured to:
use a content of the presentation information in addition to the information about temporal line-of-sight change and a timing of the switching for the determination.
5. A spoofing detection method comprising:
acquiring a facial image sequence indicating a user's face;
detecting, by a computer device, information about temporal line-of-sight change from the facial image sequence;
displaying presentation information presented to the user as part of authentication processing while switching the presentation information;
obtaining a first temporal change of a value obtained by differentiating a position of the line-of-sight with respect to time;
determining, by a computer device, a likelihood that a face indicated by the facial image sequence is spoofing, based on the information about temporal line-of-sight change with respect to the presentation information and a timing of the switching; and
using the first temporal change of the value as the information about temporal line-of-sight change for the determination.
6. A non-transitory computer readable recording medium storing a spoofing detection program causing a computer device to perform:
acquiring a facial image sequence indicating a user's face;
detecting information about temporal line-of-sight change from the facial image sequence;
displaying presentation information presented to the user as part of authentication processing while switching the presentation information;
obtaining a first temporal change of a value obtained by differentiating a position of the line-of-sight with respect to time;
determining a likelihood that a face indicated by the facial image sequence is spoofing, based on the information about temporal line-of-sight change with respect to the presentation information and a timing of the switching; and
using the first temporal change of the value as the information about temporal line-of-sight change for the determination.