US 12,260,680 B1
Device and method for determining counterfeit fingerprints and recording medium including command for performing method of training neural network to determine counterfeit fingerprints
Jong Man Lee, Seongnam-si (KR); Young Mook Kang, Seongnam-si (KR); Jae Hyun Park, Seongnam-si (KR); Hochul Shin, Seongnam-si (KR); and Bong Seop Song, Seongnam-si (KR)
Assigned to SUPREMA INC., Seongnam-si (KR)
Filed by Suprema Inc., Seongnam-si (KR)
Filed on Nov. 28, 2023, as Appl. No. 18/521,644.
Claims priority of application No. 10-2023-0143951 (KR), filed on Oct. 25, 2023.
Int. Cl. G06V 40/40 (2022.01); G06F 21/32 (2013.01); G06V 10/60 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 40/12 (2022.01); G06V 40/13 (2022.01)
CPC G06V 40/40 (2022.01) [G06F 21/32 (2013.01); G06V 10/60 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 40/1318 (2022.01); G06V 40/1347 (2022.01); G06V 40/1365 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A device for determining a counterfeit fingerprint of a system that includes an internal light source and an external light source, the device comprising:
an input unit to receive a first fingerprint image obtained from a light signal of the internal light source and a second fingerprint image obtained from the external light source when a target object's fingerprint comes in contact with a fingerprint contact surface of the system;
a storage unit to store a command for outputting a result of the determining the counterfeit fingerprint using a pre-trained neural network; and
a processing unit to extract a first fingerprint area of the first fingerprint image and a second fingerprint area of the second fingerprint image based on the first fingerprint area, to input the first fingerprint area and the second fingerprint area into the pre-trained neural network by executing the command to allow a result of the determining the counterfeit fingerprint to be output, to divide the first fingerprint image into a plurality of areas based on a light signal reflected from the internal light source to extract the first fingerprint area and extract the second fingerprint area within the first fingerprint area from a light signal transmitted from the external light source, to measure a range of brightness values of the first fingerprint area or the second fingerprint area, and to classify the target object's fingerprint as a normal fingerprint, a wet fingerprint, or a dry fingerprint based on the range of the brightness values.