De-identification of profile pictures while retaining facial features using generative adversarial networks
In this paper, we propose a method to perform de-identification of profile pictures by using Generative Adversarial Networks (GANs) to generate similar images of people. The goal is to maximally mask the identity of the individual, by making them unrecognisable to their friends and family, while ret...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/148060 |
| _version_ | 1826109851830321152 |
|---|---|
| author | Lim, Yee Han |
| author2 | Kong Wai-Kin Adams |
| author_facet | Kong Wai-Kin Adams Lim, Yee Han |
| author_sort | Lim, Yee Han |
| collection | NTU |
| description | In this paper, we propose a method to perform de-identification of profile pictures by using Generative Adversarial Networks (GANs) to generate similar images of people. The goal is to maximally mask the identity of the individual, by making them unrecognisable to their friends and family, while retaining important facial features that make them look indistinguishable to strangers. We dub this goal, “Unrecognisable To Friends, Indistinguishable To Strangers” (UTF-ITS). We achieve this by minimising the L2 loss between the reference image and the generated image, using a pre-trained model published in NVIDIA’s StyleGAN research. By prematurely stopping the minimisation of L2 loss at a desirable iteration, we can achieve the UTF-ITS goal. This process could be useful for social applications where it is necessary to reveal an individual’s facial likeness, but users might not want to reveal their identity for privacy reasons, i.e. Dating Apps, Online Forums. |
| first_indexed | 2024-10-01T02:25:11Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/148060 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:25:11Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1480602021-04-22T08:16:31Z De-identification of profile pictures while retaining facial features using generative adversarial networks Lim, Yee Han Kong Wai-Kin Adams School of Computer Science and Engineering AdamsKong@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision In this paper, we propose a method to perform de-identification of profile pictures by using Generative Adversarial Networks (GANs) to generate similar images of people. The goal is to maximally mask the identity of the individual, by making them unrecognisable to their friends and family, while retaining important facial features that make them look indistinguishable to strangers. We dub this goal, “Unrecognisable To Friends, Indistinguishable To Strangers” (UTF-ITS). We achieve this by minimising the L2 loss between the reference image and the generated image, using a pre-trained model published in NVIDIA’s StyleGAN research. By prematurely stopping the minimisation of L2 loss at a desirable iteration, we can achieve the UTF-ITS goal. This process could be useful for social applications where it is necessary to reveal an individual’s facial likeness, but users might not want to reveal their identity for privacy reasons, i.e. Dating Apps, Online Forums. Bachelor of Engineering (Computer Science) 2021-04-22T08:16:30Z 2021-04-22T08:16:30Z 2021 Final Year Project (FYP) Lim, Y. H. (2021). De-identification of profile pictures while retaining facial features using generative adversarial networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148060 https://hdl.handle.net/10356/148060 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Lim, Yee Han De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title | De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title_full | De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title_fullStr | De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title_full_unstemmed | De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title_short | De-identification of profile pictures while retaining facial features using generative adversarial networks |
| title_sort | de identification of profile pictures while retaining facial features using generative adversarial networks |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/148060 |
| work_keys_str_mv | AT limyeehan deidentificationofprofilepictureswhileretainingfacialfeaturesusinggenerativeadversarialnetworks |