dc.contributor.author | Hassan, Muhammad Umair | |
dc.contributor.author | Stava, Magnus | |
dc.contributor.author | Hameed, Ibrahim A | |
dc.date.accessioned | 2024-02-21T07:39:08Z | |
dc.date.available | 2024-02-21T07:39:08Z | |
dc.date.created | 2024-01-04T15:31:03Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | 2023 International Conference on Smart Applications, Communications and Networking (SmartNets) | en_US |
dc.identifier.isbn | 979-8-3503-0252-3 | |
dc.identifier.uri | https://hdl.handle.net/11250/3118835 | |
dc.description.abstract | Interest in privacy has increased due to the public’s increased attention given to it by the introduction of the EU’s GDPR. The number of images containing identifiable features has multiplied dramatically in an increasingly digital world where data is gathered on a large scale through surveillance systems, smartphones, cameras, etc. In order to protect our privacy, it is essential to look into methods that can anonymize individuals in real time before the digital data is stored. We look into two state-of-the-art face detectors and consider how they perform in real time. In addition, we consider multiple methods for anonymizing individuals in the loop and how it affects the resulting image. The performance is based on the WiderFace benchmark, including easy, medium, and hard subsets. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.title | Deep Privacy based Face Anonymization for Smart Cities | en_US |
dc.title.alternative | Deep Privacy based Face Anonymization for Smart Cities | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.source.journal | IEEE Xplore Digital Library | en_US |
dc.identifier.doi | 10.1109/SmartNets58706.2023.10215996 | |
dc.identifier.cristin | 2220797 | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 0 | |