IP Library › Granted Patent US 12,437,373
Granted Patent B2
US 12,437,373 · App. 18/323,718 · Granted Oct 7, 2025

Determination method, non-transitory computer-readable recording medium storing determination program, and information processing device

Inventors: Lina Septiana (Machida, JP); Tomoaki Matsunami (Kawasaki, JP); Narishige Abe (Kawasaki, JP)
Assignee: Fujitsu Limited
G06T5/70G06T2207/20224G06T2207/30201
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,437,373
App. No.
18/323,718
Granted
Oct 7, 2025
Kind
B2
Abstract

In a determination method, a computer executes processing including: generating face image data from which noise is removed by a specific algorithm from face image data when the face image data is acquired; generating difference image data concerning difference between the face image data that has been acquired and the face image data that has been generated; determining whether or not the face image data that has been acquired is a composite image based on information included in the difference image data; and determining whether or not the face image data that has been acquired is a composite image based on information included in frequency data generated from the difference image data in a case where the face image data that has been acquired is not determined to be a composite image.

Claims (36)

1. A determination method implemented by a computer, the determination method comprising:

generating face image data from which noise is removed by a specific algorithm from face image data when the face image data is acquired;

generating difference image data concerning difference between the face image data that has been acquired and the face image data that has been generated;

determining whether the face image data that has been acquired is a composite image based on information included in the difference image data; and

determining whether the face image data that has been acquired is a composite image based on information included in frequency data generated from the difference image data in a case where the face image data that has been acquired is not determined to be a composite image.

2. The determination method according to claim 1 , wherein the determining of whether the face image data that has been acquired is a composite image includes detecting a discontinuous portion of noise intensity.

3. The determination method according to claim 1 , the method further comprising: determining, using a classification model trained by using teacher data of a plurality of pieces of face image data, whether the face image data that has been determined whether or not the face image data is the composite image is a composite image.

4. The determination method according to claim 1 , wherein a color space of the face image data that has been acquired is an HSV color space.

5. The determination method according to claim 1 , the method further comprising: generating the frequency data from the difference image data by digital Fourier transform.

6. The determination method according to claim 1 , wherein the information included in the difference image data is a statistic obtained by comparing a pixel value of a pixel of interest with pixel values of pixels around the pixel of interest.

7. The determination method according to claim 1 , wherein a feature amount represented by numerical expression is used as the information included in the difference image data.

8. A non-transitory computer-readable recording medium storing a determination program for causing a computer to perform processing, the processing comprising:

generating face image data from which noise is removed by a specific algorithm from face image data when the face image data is acquired;

generating difference image data concerning difference between the face image data that has been acquired and the face image data that has been generated;

determining whether the face image data that has been acquired is a composite image based on information included in the difference image data; and

determining whether the face image data that has been acquired is a composite image based on information included in frequency data generated from the difference image data in a case where the face image data that has been acquired is not determined to be a composite image.

9. The non-transitory computer-readable recording medium according to claim 8 , wherein the determining of whether the face image data that has been acquired is a composite image includes detecting a discontinuous portion of noise intensity.

10. The non-transitory computer-readable recording medium according to claim 8 , the processing further comprising: determining, using a classification model trained by using teacher data of a plurality of pieces of face image data, whether the face image data that has been determined whether or not the face image data is the composite image is a composite image.

11. The non-transitory computer-readable recording medium according to claim 8 , wherein a color space of the face image data that has been acquired is an HSV color space.

12. The non-transitory computer-readable recording medium according to claim 8 , the processing further comprising: generating the frequency data from the difference image data by digital Fourier transform.

13. The non-transitory computer-readable recording medium according to claim 8 , wherein the information included in the difference image data is a statistic obtained by comparing a pixel value of a pixel of interest with pixel values of pixels around the pixel of interest.

14. The non-transitory computer-readable recording medium according to claim 8 , wherein a feature amount represented by numerical expression is used as the information included in the difference image data.

15. An information processing device comprising:

memory; and

processor circuitry coupled to the memory, the processor circuitry being configured to perform processing including:

generating face image data from which noise is removed by a specific algorithm from face image data when the face image data is acquired;

generating difference image data concerning difference between the face image data that has been acquired and the face image data that has been generated;

determining whether the face image data that has been acquired is a composite image based on information included in the difference image data; and

determining whether the face image data that has been acquired is a composite image based on information included in frequency data generated from the difference image data in a case where the face image data that has been acquired is not determined to be a composite image.

16. The information processing device according to claim 15 , wherein

the determining of whether the face image data that has been acquired is a composite image includes detecting a discontinuous portion of noise intensity.

17. The information processing device according to claim 15 , the processing further comprising: determining, using a classification model trained by using teacher data of a plurality of pieces of face image data, whether the face image data that has been determined whether or not the face image data is the composite image is a composite image.

18. The information processing device according to claim 15 , wherein a color space of the face image data that has been acquired is an HSV color space.

19. The information processing device according to claim 15 , the processing further comprising: generating the frequency data from the difference image data by digital Fourier transform.

20. The information processing device according to claim 15 , wherein the information included in the difference image data is a statistic obtained by comparing a pixel value of a pixel of interest with pixel values of pixels around the pixel of interest.

21. The information processing device according to claim 15 , wherein a feature amount represented by numerical expression is used as the information included in the difference image data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 25, 2023
From: SEPTIANA, LINA; MATSUNAMI, TOMOAKI; ABE, NARISHIGE
To: FUJITSU LIMITED
Reel/Frame 063765/0036 →
Continuity (2)
Continuation PCTJP2021002736 · Jan 27, 2021
Related Publication 20230298140A1 · Sep 21, 2023
References Cited (23)
US 10762337B2 · Sharma · 2020 [cited by examiner]
US 20170084007A1 · Rakhshanfar · 2017 [cited by examiner]
US 20200218885A1 · Darmstadt · 2020 [cited by applicant]
US 20200364834A1 · Ferrés · 2020 [cited by examiner]
US 20210097297A1 · Ren · 2021 [cited by examiner]
US 20220207260A1 · Dong · 2022 [cited by examiner]
US 20250157253A1 · Islam · 2025 [cited by examiner]
JP 2015503866A · 2015 [cited by applicant]
JP 2019096130A · 2019 [cited by applicant]
JP 2020525947A · 2020 [cited by applicant]
WO 2013100898A1 · 2013 [cited by applicant]
WO 2019002602A1 · 2019 [cited by applicant]
Sushma Venkatesh, Raghavendra Ramachandra, Kiran Raja, Luuk Spreeuwers, Raymond Veldhuis, Christoph Busch; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 280-289 (Year… [cited by examiner]
U. Scherhag, L. Debiasi, C. Rathgeb, C. Busch and A. Uhl, “Detection of Face Morphing Attacks Based on PRNU Analysis,” in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 1, No. 4, pp. 302-317, Oct.… [cited by examiner]
Tom Neubert, Christian Kraetzer, and Jana Dittmann. 2019. A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD . In ACM Information Hiding and Multimedia Security Wor… [cited by examiner]
S. Venkatesh, R. Ramachandra, K. Raja, L. Spreeuwers, R. Veldhuis and C. Busch, “Morphed Face Detection Based on Deep Color Residual Noise,” 2019 Ninth International Conference on Image Processing Theory, Tools and Appl… [cited by examiner]
Pikoulis, E.-V., Ioannou, Z.-M., Paschou, M., & Sakkopoulos, E. (2021). Face Morphing, a Modern Threat to Border Security: Recent Advances and Open Challenges. Applied Sciences, 11(7), 3207. https://doi.org/10.3390/app1… [cited by examiner]
Sharafudeen, M., Chandra S S, V. Frequency forensics for deep fake face detection using dual residual networks. Multimed Tools Appl (2025). https://doi.org/10.1007/s11042-025-20897-w (Year: 2025). [cited by examiner]
Christian Rathgeb et al., “PRNU-based detection of facial retouching”, IET Biometrics, IEEE, Michael Faraday House, Six Hills Way, Stevenage, HERTS.SG1 2AY, UK, vol. 9, No. 4, XP006090764, pp. 154-164, Jul. 1, 2020. Cit… [cited by applicant]
Sushma Venkatesh et al., “Face Morphing Attack Generation & Detection: A Comprehensive Survey”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, XP081807368, 18 pages, Nov. 3,… [cited by applicant]
EESR—Extended European Search Report mailed on Dec. 8, 2023 for corresponding European Patent Application No. 21922784.0 (4 pages). [cited by applicant]
Xinrui Yu et al., “Face Morphing Detection using Generative Adversarial Networks”, 2019 IEEE International Conference on Electro Information Technology(EIT), pp. 288-291, May 22, 2019 (Total 4 pages) (Cited in ISR). [cited by applicant]
International Search Report and Written Opinion of the International Searching Authority (Form PCT/ISA/210, 220, and 237), mailed in connection with PCT/JP2021/002736 and mailed Apr. 13, 2021 (Total 10 pages). [cited by applicant]