TY - GEN
T1 - Face De-identification Scheme Using Landmark-Based Inpainting
AU - Kim, Hyeonwoo
AU - Lee, Junsuk
AU - Hwang, Eenjun
N1 - Funding Information:
ACKNOWLEDGMENT This research was supported in part by the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. NRF-2020R1F1A1074885) and in part by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2021R1A4A1031864).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Due to the spread of various information and communication technologies, a huge amount of images are produced and shared for diverse purposes. Several de-identification techniques for photos, such as pixelation, blur, and mask, are routinely used in light of recent worries about the growing number of privacy leakages. However, due to the low image quality and loss of many facial features, these de-identified images are not suitable for use in applications such as training models that require a lot of high-quality data. Therefore, in this paper, we propose a new face de-identification method focusing only on facial regions essential for personal identification. By generating facial landmarks differently from the original person using masking and generative adversarial networks-based inpainting, our method can perform de-identification efficiently. To demonstrate the performance of our proposed scheme, we conducted quantitative and qualitative evaluations using an open dataset. We show that our proposed scheme outperforms other de-identification methods.
AB - Due to the spread of various information and communication technologies, a huge amount of images are produced and shared for diverse purposes. Several de-identification techniques for photos, such as pixelation, blur, and mask, are routinely used in light of recent worries about the growing number of privacy leakages. However, due to the low image quality and loss of many facial features, these de-identified images are not suitable for use in applications such as training models that require a lot of high-quality data. Therefore, in this paper, we propose a new face de-identification method focusing only on facial regions essential for personal identification. By generating facial landmarks differently from the original person using masking and generative adversarial networks-based inpainting, our method can perform de-identification efficiently. To demonstrate the performance of our proposed scheme, we conducted quantitative and qualitative evaluations using an open dataset. We show that our proposed scheme outperforms other de-identification methods.
KW - De-identification
KW - Generative adversarial network
KW - Image inpainting
UR - http://www.scopus.com/inward/record.url?scp=85137943845&partnerID=8YFLogxK
U2 - 10.1109/HSI55341.2022.9869487
DO - 10.1109/HSI55341.2022.9869487
M3 - Conference contribution
AN - SCOPUS:85137943845
T3 - International Conference on Human System Interaction, HSI
BT - 15th IEEE International Conference on Human System Interaction, HSI 2022
PB - IEEE Computer Society
T2 - 15th IEEE International Conference on Human System Interaction, HSI 2022
Y2 - 28 July 2022 through 31 July 2022
ER -