US 12,438,849 B2
Face anonymization using a generative adversarial network
Yi Estelle Wang, Singapore (SG); Liming Zhai, Singapore (SG); Qing Guo, Singapore (SG); and Jeremy Dahan, Fair Oaks, CA (US)
Assigned to Elektrobit Automotive GmbH, Erlangen (DE); and NANYANG TECHNOLOGICAL UNIVERSITY, Singapore (SG)
Filed by Elektrobit Automotive GmbH, Erlangen (DE); and NANYANG TECHNOLOGICAL UNIVERSITY, Singapore (SG)
Filed on Apr. 5, 2023, as Appl. No. 18/131,147.
Claims priority of application No. 22166968 (EP), filed on Apr. 6, 2022.
Prior Publication US 2023/0328039 A1, Oct. 12, 2023
Int. Cl. H04L 9/40 (2022.01); G06F 21/62 (2013.01); G06T 7/00 (2017.01); G06T 11/60 (2006.01)
CPC H04L 63/0421 (2013.01) [G06F 21/6254 (2013.01); G06T 7/0002 (2013.01); G06T 11/60 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30168 (2013.01); G06T 2207/30201 (2013.01); G06T 2207/30252 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by a processor, perform operations face anonymization, the operations comprising:
receiving an input image showing a face to be anonymized;
receiving an input vector with control data for face anonymization; and
generating by a generative adversarial network, an output image in which the face is anonymized in accordance with the control data of the input vector, wherein the generative adversarial network comprises a generator sub-network trained to generate new faces with different facial attributes, a discriminator sub-network trained to evaluate if generated new faces are realistic and natural, and an identity classifier sub-network trained to evaluate if face identities of new faces have been changed, and wherein the generator sub-network, the discriminator sub-network and the identity classifier sub-network are trained alternately and compete with each other to achieve balance of optimization.