US-20260127859-A1 - METHOD AND APPARATUS FOR FAKE FINGERPRINTS GENERATION, AND TRAINING METHOD OF ARTIFICIAL INTELLIGENCE FOR IDENTIFYING FAKE FINGERPRINTS

US20260127859A1US 20260127859 A1US20260127859 A1US 20260127859A1US-20260127859-A1

Abstract

There is provided a method for generating a fake fingerprint, performed by a fingerprint generating device, the method comprising: acquiring a fingerprint image targeting a fingerprint of a finger; extracting unique identification information of a fingerprint from the fingerprint image; providing the unique identification information and generation constraints to a training fingerprint image generating model; and generating a training fingerprint image to be used for training a fake fingerprint detection model by using the training fingerprint image generation model, so that the unique identification information of the training fingerprint image is mapped onto a real fingerprint of the finger.

Inventors

Beom Jun KIM
Jong Man Lee
Hochul SHIN
Jae Hyun Park
Young Mook KANG

Assignees

SUPREMA INC.

Dates

Publication Date: 20260507
Application Date: 20241212
Priority Date: 20241106

Claims (18)

1 . A method for generating a fake fingerprint, performed by a fingerprint generating device, the method comprising: acquiring a fingerprint image targeting a fingerprint of a finger; extracting unique identification information of a fingerprint from the fingerprint image; providing the unique identification information and generation constraints to a training fingerprint image generation model, wherein the training fingerprint image generation model is trained to generate different training fingerprint images based on conditions included in the generation constraints; and generating a training fingerprint image to be used for training a fake fingerprint detection model by using the training fingerprint image generation model.
2 . The method of claim 1 , wherein the fingerprint image includes an image obtained by capturing a real fingerprint of the finger or an image obtained from the training fingerprint image generation model.
3 . The method of claim 2 , wherein the unique identification information includes at least one of first identification information based on start points, end points and branch points of ridges in the fingerprint of the finger, second identification information based on orientations of the ridges, and third identification information based on a distribution density of the ridges.
4 . The method of claim 1 , wherein the generation constraints include information about a sensor that identifies a fingerprint, information about surrounding environment in which the fingerprint is identified, and labeling information about the fingerprint.
5 . The method of claim 4 , wherein the labeling information includes information about whether the fingerprint is a real fingerprint or a fake fingerprint and information about a type of means used to generate the fake fingerprint.
6 . The method of claim 1 , wherein the fake fingerprint is obtained from the finger by means of at least one of silicone, latex, paper and glue.
7 . (canceled)
8 . The method of claim 1 , further comprising acquiring random noise, wherein the training fingerprint image generation model generates different training fingerprint images according to the random noise even when a same generation constraints are applied.
9 . A method for training a fake fingerprint detection model, performed by a training device for an artificial intelligence model, the method comprising: acquiring a fingerprint image targeting a fingerprint of a finger; extracting unique identification information of a fingerprint from the fingerprint image; providing the unique identification information and generation constraints to a training fingerprint image generating model, wherein the training fingerprint image generation model is trained to generate different training fingerprint images based on conditions included in the generation constraints; generating a training fingerprint image to be used for training a fake fingerprint detection model by using the training fingerprint image generation model; and training the fake fingerprint detection model using at least one of the acquired-training fingerprint image and an image obtained from a real fingerprint.
10 . The method of claim 9 , wherein the fingerprint image includes an image obtained by capturing the real fingerprint or an image obtained from the training fingerprint image generation model.
11 . The method of claim 10 , wherein the unique identification information includes at least one of first identification information based on start points, end points and branch points of ridges in the fingerprint of the finger, second identification information based on orientations of the ridges, and third identification information based on a distribution density of the ridges.
12 . The method of claim 9 , wherein the generation constraints include information about a sensor that identifies the fingerprint, information about surrounding environment in which the fingerprint is identified, and labeling information about the fingerprint.
13 . The method of claim 12 , wherein the labeling information includes information about whether the fingerprint is a real fingerprint or a fake fingerprint and information about a type of means used to generate the fake fingerprint.
14 . The method of claim 9 , wherein a fake fingerprint is obtained from the finger by means of at least one of silicone, latex, paper and glue.
15 . The method of claim 9 , wherein the training fingerprint image generation model is trained to generate different training fingerprint images based on conditions included in the generation constraints.
16 . The method of claim 9 , further comprising acquiring random noise, wherein the training fingerprint image generation model generates different training fingerprint images according to the random noise even when a same generation constraints are applied.
17 . A fingerprint generation device comprising: a memory storing computer-executable instructions; and a processor for executing the instructions to: acquire a fingerprint image targeting a fingerprint of a finger; extract unique identification information of a fingerprint from the fingerprint image; and provide the unique identification information and generation constraints to a training fingerprint image generation model to obtain a training fingerprint image to be used for training a fake fingerprint detection model by using the training fingerprint image generation model, wherein the training fingerprint image generation model is trained to generate different training fingerprint images based on conditions included in the generation constraints.
18 . (canceled)

Description

CROSS-REFERENCE TO RELATED APPLICATION This application claims priority to Korean Patent Application No. 10-2024-0156218, filed on Nov. 6, 2024, the entirety of which is incorporated herein by reference for all purposes. TECHNICAL FIELD The present disclosure relates to a method and device for generating fake fingerprints, and a method for training an artificial intelligence model for detecting fake fingerprints. This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (Ministry of Science and ICT) (Project unique No.: 2710007816; Project No.: II201787; R&D project: Information and Communication Broadcasting Innovation Talent Training (R&D); Research Project Title: Development of communication/computing convergence innovation technology for super-intelligent services; and Project period: 2024.01.01.˜2024.12.31.). BACKGROUND Fingerprint recognition is one of the most widely used biometric technologies today, and is rapidly replacing passwords composed of letters or patterns in daily life. Many people perceive fingerprint recognition technology as being more resistant to leakage or duplicate than passwords composed of letters or patterns, however fingerprints are not free from the risk of duplication. Therefore, if a fingerprint is exposed and duplicated by a third party, the duplicated fake fingerprint may be used to obtain authentication. Meanwhile, fingerprints can be easily exposed to the outside world, such as being left on objects touched by the hand, which leads to a security vulnerability. Accordingly, the development of technologies to distinguish between real fingerprints and fake fingerprints (e.g., the development of fake fingerprint detection technology using artificial intelligence) is actively underway. However, there is a limitation in improving the performance of the fake fingerprint detection models due to insufficient training data to train artificial intelligence algorithms used for detect fake fingerprints. SUMMARY In view of the above, the present disclosure provides a method for generating a large amount of training data required to training an artificial intelligence model for detecting fake fingerprints. In addition, the present disclosure provides a method for training a fake fingerprint detection model using training data generated by the aforementioned method. However, the problem to be solved by the present disclosure is not limited to that mentioned above, and other problems to be solved that are not mentioned may be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the following description. In accordance with an aspect of the present disclosure, there is provided a method for generating a fake fingerprint, performed by a fingerprint generating device, the method comprising: acquiring a fingerprint image targeting a fingerprint of a finger; extracting unique identification information of a fingerprint from the fingerprint image; providing the unique identification information and generation constraints to a training fingerprint image generating model; and generating a training fingerprint image to be used for training a fake fingerprint detection model by using the training fingerprint image generation model, so that the unique identification information of the training fingerprint image is mapped onto a real fingerprint of the finger. The fingerprint image may include an image obtained by capturing the real fingerprint or an image obtained from the training fingerprint image generation model. The unique identification information may include at least one of first identification information based on start points, end points and branch points of ridges in the fingerprint of the finger, second identification information based on orientations of the ridges, and third identification information based on a distribution density of the ridges. The generation constraints may include information about a sensor that identifies a fingerprint, information about surrounding environment in which the fingerprint is identified, and labeling information about the fingerprint. The labeling information may include information about whether the fingerprint is a real fingerprint or a fake fingerprint and information about a type of means used to generate the fake fingerprint. The fake fingerprint may be obtained from the finger by means of at least one of silicone, latex, paper and glue. The training fingerprint image generation model may be trained to generate different training fingerprint images based on conditions included in the generation constraints while freezing the unique identification information. The method may further comprise acquiring random noise, wherein the training fingerprint image generation model may generate different training fingerprint images according to the random noise even when the same generation constraints are applied. In accor