Granted Patent B2

US 12,738,102 · App. 19/213,340 · Granted Sep 15, 2026

Inventors: Juhyoun Shim (Suwon-si, KR); Moonsoo Chang (Suwon-si, KR)

Assignee: Samsung Electronics Co., Ltd.

G06V40/50G06F21/32G06V10/82G06V40/1318G06V40/1365G06V40/40

Abstract

Claims (68)

1 . An electronic device comprising:

a sensor;

memory configured to store a plurality of registered fingerprint templates, each of the plurality of registered fingerprint templates comprising at least one embedding vector indicating a respective one of a plurality of registered fingerprint images, and at least one computer program; and

at least one processor communicatively coupled to the sensor and the memory,

wherein the plurality of registered fingerprint images comprises a forged fingerprint image made by forging a fingerprint of a user, an abnormal state fingerprint image comprising an obstacle obstructing fingerprint authentication, and a normal state fingerprint image which is either a successfully registered fingerprint image or a fingerprint image matching the successfully registered fingerprint image, and

wherein the at least one computer program comprises instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:

acquire, using the sensor, an input fingerprint image indicating a fingerprint image input by the user,

generate an input fingerprint template from the input fingerprint image,

compare the input fingerprint template and the plurality of registered fingerprint templates,

identify whether the input fingerprint template matches at least a part of the plurality of registered fingerprint templates, based on the comparison,

in case that the input fingerprint template matches the at least a part of the plurality of registered fingerprint templates, generate, using a fingerprint generation artificial intelligence model, at least one virtual fingerprint image representing a fingerprint of the user in at least one of an abnormal state or a forged state, based on the input fingerprint image,

generate at least one virtual fingerprint template from the at least one virtual fingerprint image,

store the input fingerprint template and the at least one virtual fingerprint template in the memory, and

train the fingerprint generation artificial intelligence model based on the input fingerprint image.

2 . The electronic device of claim 1 , wherein the instructions further comprise an instruction that, when executed by the at least one processor individually or collectively, cause the electronic device to train an anti-spoofing-protection (ASP) circuitry configured to determine whether the input fingerprint image is a forged image, based on the input fingerprint image matching the at least a part of the plurality of registered fingerprint images and the at least one virtual fingerprint image.

3 . The electronic device of claim 2 , wherein the instructions further comprise instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:

use the ASP circuitry to determine whether the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is a forged fingerprint image;

in case of determining that the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is a forged fingerprint image, determine that fingerprint authentication has failed; and

in case of determining that the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is not a forged fingerprint image, determine that fingerprint authentication has succeeded.

4 . The electronic device of claim 1 , wherein the instructions further comprise an instruction that, when executed by the at least one processor individually or collectively, cause the electronic device to

based on a plurality of comparison values, classify the input fingerprint image matching the at least a part of the plurality of registered fingerprint images as one of the forged fingerprint image, the abnormal state fingerprint image, or the normal state fingerprint image.

5 . The electronic device of claim 4 , wherein the instructions further comprise instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:

based on the classified input fingerprint image, generate a virtual fingerprint image corresponding to the classified input fingerprint image; and

store a template of the generated virtual fingerprint image as a corresponding template among a template of the forged fingerprint image, a template of the abnormal state fingerprint image, and a template of the normal state fingerprint image.

6 . The electronic device of claim 5 , wherein the instructions further comprise instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to

generate the at least one virtual fingerprint image corresponding to the input fingerprint image in the case that the input fingerprint image is clearly acquired and has recognizable structural characteristics, and

wherein a template of the input fingerprint image and a template of the at least one virtual fingerprint image are stored in the plurality of registered fingerprint templates.

7 . The electronic device of claim 6 , wherein the instructions further comprise instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:

receive another input fingerprint image for authentication; and

in response to receiving the other input fingerprint image for authentication, determine whether the other input fingerprint image matches at least a part of the plurality of registered fingerprint images including the input fingerprint image and the at least one virtual fingerprint image.

8 . The electronic device of claim 4 , wherein the abnormal state fingerprint image comprises a fingerprint image in a wet state or a fingerprint image in a dry state.

9 . The electronic device of claim 1 , wherein the instructions further comprise an instruction that, when executed by the at least one processor individually or collectively, cause the electronic device to, in case that the input fingerprint image does not match the at least a part of the plurality of registered fingerprint images, determine that fingerprint authentication of the input fingerprint image has failed.

10 . The electronic device of claim 1 ,

wherein the processor comprises at least one neural processing unit (NPU), and

wherein the processor is configured to generate the at least one virtual fingerprint image by using the at least one NPU.

11 . The electronic device of claim 1 ,

wherein the memory is configured to store templates corresponding to multiple users, and

wherein the instructions further comprise instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:

acquire an input fingerprint image by using the sensor, and

specify a user of the input fingerprint image, based on the templates corresponding to the multiple users.

12 . A method performed by an electronic device, the method comprising:

acquiring, using a sensor, an input fingerprint image corresponding to a fingerprint image input by a user;

generating an input fingerprint template from the input fingerprint image;

comparing the input fingerprint template and a plurality of registered fingerprint templates;

identifying whether the input fingerprint template matches at least a part of the plurality of registered fingerprint templates, based on a result obtained by comparing a plurality of comparison values and a threshold value,

wherein each of the plurality of registered fingerprint templates comprises at least one embedding vector indicating a respective one of a plurality of registered fingerprint images,

wherein the plurality of registered fingerprint images comprises a forged fingerprint image made by forging a fingerprint of the user, an abnormal state fingerprint image comprising an obstacle obstructing fingerprint authentication, and a normal state fingerprint image which is either a successfully registered fingerprint image or a fingerprint image matching the successfully registered fingerprint image;

in case that the input fingerprint template matches the at least a part of the plurality of registered fingerprint templates, generating, using a fingerprint generation artificial intelligence model, at least one virtual fingerprint image representing a fingerprint of the user in at least one of an abnormal state or a forged state, based on the input fingerprint image;

generating at least one virtual fingerprint template from the at least one virtual fingerprint image;

storing the input fingerprint template and the at least one virtual fingerprint template in memory; and

training the fingerprint generation artificial intelligence model based on the input fingerprint image.

13 . The method of claim 12 , the method further comprising:

training an anti-spoofing-protection (ASP) circuitry configured to determine whether the input fingerprint image is a forged image, based on the input fingerprint image matching the at least a part of the plurality of registered fingerprint images and the at least one virtual fingerprint image.

14 . The method of claim 13 , the method further comprising:

using the anti-spoofing-protection (ASP) circuitry to determine whether the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is a forged fingerprint image;

in case of determining that the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is a forged fingerprint image, determining that fingerprint authentication has failed; and

in case of determining that the input fingerprint image matching the at least a part of the plurality of registered fingerprint images is not a forged fingerprint image, determining that fingerprint authentication has succeeded.

15 . The method of claim 12 , the method further comprising:

classifying the input fingerprint image matching the at least a part of the plurality of registered fingerprint images as one of a forged fingerprint image, an abnormal state fingerprint image, or a normal state fingerprint image.

16 . The method of claim 15 , the method further comprising:

based on the classified input fingerprint image, generating a virtual fingerprint image corresponding to the classified input fingerprint image; and

storing a template of the generated virtual fingerprint image as a corresponding template among a template of the forged fingerprint image, a template of the abnormal state fingerprint image, and a template of the normal state fingerprint image.

17 . The method of claim 16 ,

generate the at least one virtual fingerprint image corresponding to the input fingerprint image in the case that the input fingerprint image is clearly acquired and has recognizable structural characteristics, and

wherein a template of the input fingerprint image and a template of the at least one virtual fingerprint image are stored in the plurality of registered fingerprint templates.

18 . The method of claim 17 , the method further comprising:

receiving another input fingerprint image for authentication; and

in response to receiving the other input fingerprint image for authentication, determining whether the other input fingerprint image matches at least a part of the plurality of registered fingerprint images the input fingerprint image and the at least one virtual fingerprint image.

Assignments (1)

Priority Claims (2)

Continuity (2)

References Cited (26)