US 12,387,527 B2
Detecting forged facial images using frequency domain information and local correlation
Taiping Yao, Shenzhen (CN); Shen Chen, Shenzhen (CN); Yang Chen, Shenzhen (CN); Shouhong Ding, Shenzhen (CN); Jilin Li, Shenzhen (CN); and Feiyue Huang, Shenzhen (CN)
Assigned to Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Guangdong (CN)
Filed on Nov. 21, 2022, as Appl. No. 17/991,632.
Application 17/991,632 is a continuation of application No. PCT/CN2022/073249, filed on Jan. 21, 2022.
Claims priority of application No. 202110116762.8 (CN), filed on Jan. 28, 2021.
Prior Publication US 2023/0081645 A1, Mar. 16, 2023
Int. Cl. G06V 40/16 (2022.01); G06V 10/80 (2022.01)
CPC G06V 40/171 (2022.01) [G06V 10/80 (2022.01)] 19 Claims
OG exemplary drawing
 
1. An image detection method, comprising:
obtaining a facial image;
obtaining a frequency-domain image of the facial image and a spatial-domain feature of the facial image, the frequency-domain image being obtained by performing frequency-domain transformation on the facial image, and the spatial-domain feature being obtained by performing feature extraction on the facial image;
performing feature extraction based on the frequency-domain image, to obtain a frequency-domain feature of the facial image;
fusing the spatial-domain feature and the frequency-domain feature by using an attention fusion network of a facial image detection model, to obtain a fused feature of the facial image; and
obtaining a detection result of the facial image based on the fused feature, the detection result indicating whether the facial image is a forged facial image.