	US 12,266,211 B2
	Forgery detection of face image
Jianmin Bao, Redmond, WA (US); Dong Chen, La Jolla, CA (US); Hao Yang, Redmond, WA (US); Ting Zhang, Redmond, WA (US); Fang Wen, Beijing (CN); Baining Guo, Redmond, WA (US); and Lingzhi Li, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Appl. No. 17/777,572
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
PCT Filed Nov. 11, 2020, PCT No. PCT/US2020/059942 § 371(c)(1), (2) Date May 17, 2022, PCT Pub. No. WO2021/137946, PCT Pub. Date Jul. 8, 2021.
Claims priority of application No. 201911404028.0 (CN), filed on Dec. 30, 2019.
Prior Publication US 2023/0021661 A1, Jan. 26, 2023
Int. Cl. G06V 10/75 (2022.01); G06V 10/26 (2022.01); G06V 10/82 (2022.01); G06V 40/16 (2022.01); G06V 40/40 (2022.01)

CPC G06V 40/16 (2022.01) [G06V 10/26 (2022.01); G06V 10/754 (2022.01); G06V 10/82 (2022.01); G06V 40/161 (2022.01); G06V 40/168 (2022.01); G06V 40/40 (2022.01); G06V 10/759 (2022.01); G06V 40/172 (2022.01)]

14 Claims

1. A computer-implemented method, comprising:

obtaining an input image comprising a face;

detecting a blending boundary in the input image; and

generating, based on the detecting, a grayscale image associated with the input image, the grayscale image indicating whether the face in the input image is forged, wherein generating the corresponding grayscale image comprises:

detecting a plurality of facial landmarks in the real image;

determining, based on the plurality of facial landmarks, a mask image for replacement of at least a part of a face by performing random shape deformation on a mask region in the mask image; and

generating, based on the mask image, the corresponding grayscale image.