Detection system, detection method, and computer-readable recording medium
A spoofing detection apparatus includes a face image obtaining unit that obtains a first image frame that includes the face of a person when emitting light and a second image frame that includes the face of the person when not emitting light, a face information extraction unit that extract, from the first image frame, a first face information specifying a face portion, and extract, from the second image frame, a second face information specifying a face portion, a feature calculation unit that extracts a portion that includes a bright point in an iris region of an eye based on the first face information, extracts a portion corresponding to the portion that includes the bright point based on the second face information, and calculates a feature that is independent of the position of the bright point, and a spoofing determination unit that determines authenticity of person based on the feature.
1 . A detection system comprising:
at least one memory storing instructions; and
at least one processor connected to the memory and configured to execute the instructions to:
control a light-emitting apparatus and an image capture apparatus to obtain a first face image when light is emitted by the light emitting-apparatus and a second face image when light from the light-emitting apparatus is turned off;
convert a face image into a feature that is independent of a position of a bright point of an iris region in the face image;
calculate the feature by calculating differences between a luminance value of each pixel of an iris image of the first face image and a luminance value of each pixel of an iris image of the second face image and sorting the calculated differences in one of ascending order and descending order; and
determine an authenticity using a feature converted from the first image with a feature converted from the second image.
2 . The detection system according to claim 1 ,
further at least one processor configured to execute the instructions to
obtain a difference between a luminance distribution of the first face image and a luminance distribution of the second face image,
calculate a second feature that is independent of a reflection coefficient based on the obtained difference, and
integrate the converted feature and the calculated second feature.
3 . The detection system according to claim 2 ,
further at least one processor configured to execute the instructions to
calculate the second feature by calculating ratios between a luminance value of each pixel of the first face image and a luminance value of each pixel of the second face image and sorting the calculated ratios in one of ascending order and descending order.
4 . The detection system according to claim 1 ,
further at least one processor configured to execute the instructions to
determine a reality of a face included in the first face image and the second face image using the feature converted from the first image with the feature converted from the second image,
stop a process of determining the authenticity for a face determined not to be real, and
continue the process of determining the authenticity for a face determined to be real.
5 . The detection system according to claim 1 ,
where a light-emitting period of the light-emitting apparatus is 300 milliseconds,
further at least one processor configured to execute the instructions to
obtain the first face image in 150 milliseconds after light emission is started and the second face image in 150 milliseconds after the light was turned off.
6 . A detection method comprising:
controlling a light-emitting apparatus and an image capture apparatus to obtain a first face image when light is emitted by the light emitting-apparatus and a second face image when light from the light-emitting apparatus is turned off;
converting a face image into a feature that is independent of a position of a bright point of an iris region in the face image;
calculating the feature by calculating differences between a luminance value of each pixel of an iris image of the first face image and a luminance value of each pixel of an iris image of the second face image and sorting the calculated differences in one of ascending order and descending order; and
determining an authenticity using a feature converted from the first image with a feature converted from the second image.
7 . A non-transitory computer-readable recording medium on which a program is recorded, the program comprising instructions that cause a computer to carry out:
controlling a light-emitting apparatus and an image capture apparatus to obtain a first face image when light is emitted by the light emitting-apparatus and a second face image when light from the light-emitting apparatus is turned off;
converting a face image into a feature that is independent of a position of a bright point of an iris region in the face image;
calculating the feature by calculating differences between a luminance value of each pixel of an iris image of the first face image and a luminance value of each pixel of an iris image of the second face image and sorting the calculated differences in one of ascending order and descending order; and
determining an authenticity using a feature converted from the first image with a feature converted from the second image.