US 12,300,026 B2
Method and apparatus for deidentifying driver image dataset
Jung-Gyu Kang, Daejeon (KR); Kyoung-Wook Min, Daejeon (KR); Jae-Hyuck Park, Daejeon (KR); Doo-Seop Choi, Daejeon (KR); and Jeong-Dan Choi, Daejeon (KR)
Assigned to Electronics and Telecommunciations Research Institute, Daejeon (KR)
Filed by Electronics and Telecommunications Research Institute, Daejeon (KR)
Filed on Jan. 13, 2022, as Appl. No. 17/575,317.
Claims priority of application No. 10-2021-0111059 (KR), filed on Aug. 23, 2021.
Prior Publication US 2023/0058530 A1, Feb. 23, 2023
Int. Cl. G06V 40/16 (2022.01); G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 20/59 (2022.01)
CPC G06V 40/168 (2022.01) [G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 20/597 (2022.01); G06V 40/172 (2022.01); G06T 2207/30201 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A method for deidentifying a driver image dataset, comprising:
generating a combination dataset including pieces of combination data, each of which is configured with a preset number of pieces of driver image data included in the driver image dataset;
extracting face shape information from each of the preset number of pieces of driver image data included in the driver image dataset; and
generating a deidentified dataset using the combination dataset and the face shape information,
wherein the combination data is generated by sampling the preset number of pieces of driver image data included in the driver image dataset.