{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T14:54:46Z","timestamp":1775228086166,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T00:00:00Z","timestamp":1665100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T00:00:00Z","timestamp":1665100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Privacy protection in the computer vision field has attracted increasing attention. Generative adversarial network-based methods have been explored for identity anonymization, but they do not take into consideration semantic information of images, which may result in unrealistic or flawed facial results. In this paper, we propose a Semantic-aware De-identification Generative Adversarial Network (SDGAN) model for identity anonymization. To retain the facial expression effectively, we extract the facial semantic image using the edge-aware graph representation network to constraint the position, shape and relationship of generated facial key features. Then the semantic image is injected into the generator together with the randomly selected identity information for de-Identification. To ensure the generation quality and realistic-looking results, we adopt the SPADE architecture to improve the generation ability of conditional GAN. Meanwhile, we design a hybrid identity discriminator composed of an image quality analysis module, a VGG-based perceptual loss function, and a contrastive identity loss to enhance both the generation quality and ID anonymization. A comparison with the state-of-the-art baselines demonstrates that our model achieves significantly improved de-identification (De-ID) performance and provides more reliable and realistic-looking generated faces. Our code and data are available on <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/kimhyeongbok\/SDGAN\">https:\/\/github.com\/kimhyeongbok\/SDGAN<\/jats:ext-link><\/jats:p>","DOI":"10.1007\/s11042-022-13917-6","type":"journal-article","created":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T07:05:17Z","timestamp":1665126317000},"page":"15535-15551","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Semantic-aware deidentification generative adversarial networks for identity anonymization"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2264-9962","authenticated-orcid":false,"given":"Hyeongbok","family":"Kim","sequence":"first","affiliation":[]},{"given":"Zhiqi","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Lingling","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xiaohong","family":"Su","sequence":"additional","affiliation":[]},{"given":"Jin Suk","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,7]]},"reference":[{"key":"13917_CR1","doi-asserted-by":"crossref","unstructured":"Boyle M, Edwards C, Greenberg S (2000) The effects of filtered video on awareness and privacy. In: Proceedings of the 2000 ACM conference on computer supported cooperative work, pp 1\u201310","DOI":"10.1145\/358916.358935"},{"key":"13917_CR2","unstructured":"Breve B, Caruccio L, Cirillo S, Desiato D, Deufemia V, Polese G (2020) Enhancing user awareness during internet browsing. In: ITASEC, pp 71\u201381"},{"key":"13917_CR3","doi-asserted-by":"crossref","unstructured":"Chen BC, Chen CS, Hsu WH (2014) Cross-age reference coding for age-invariant face recognition and retrieval. In: Proceedings of the European conference on computer vision, pp 768\u2013783","DOI":"10.1007\/978-3-319-10599-4_49"},{"key":"13917_CR4","doi-asserted-by":"crossref","unstructured":"Cheng K, Zhang Y, He X, Chen W, Cheng J, Lu H (2020) Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 183\u2013192","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"13917_CR5","unstructured":"Desiato D (2018) A methodology for GDPR compliant data processing. In: SEBD"},{"key":"13917_CR6","doi-asserted-by":"crossref","unstructured":"Gafni O, Wolf L, Taigman Y (2019) Live face de-identification in video. In: Proceedings of the IEEE international conference on computer vision, pp 9378\u20139387","DOI":"10.1109\/ICCV.2019.00947"},{"key":"13917_CR7","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. (2014) Generative adversarial nets. In: Proceedings of Advances in neural information processing systems, pp 2672\u20132680"},{"key":"13917_CR8","doi-asserted-by":"crossref","unstructured":"Gross R, Sweeney L, De la Torre F, Baker S (2006) Model-based face de-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshop, pp 161\u2013161","DOI":"10.1109\/CVPRW.2006.125"},{"key":"13917_CR9","doi-asserted-by":"crossref","unstructured":"Gu X, Luo W, Ryoo MS, Lee YJ (2020) Password-conditioned anonymization and deanonymization with face identity transformers. In: European conference on computer vision, pp 727\u2013743","DOI":"10.1007\/978-3-030-58592-1_43"},{"key":"13917_CR10","doi-asserted-by":"crossref","unstructured":"Guo K, Hu X, Li X (2021) MMFGAN: A novel multimodal brain medical image fusion based on the improvement of generative adversarial network. Multimedia Tools and Applications, pp 1\u201339","DOI":"10.1007\/s11042-021-11822-y"},{"key":"13917_CR11","doi-asserted-by":"crossref","unstructured":"Guo J, Pang Z, Bai M, Xie P, Chen Y (2021) Dual generative adversarial active learning. Appl Intell, pp 1\u201312","DOI":"10.1007\/s10489-020-02121-4"},{"key":"13917_CR12","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, pp 6626\u20136637"},{"key":"13917_CR13","unstructured":"Huan GB, Mattar M, Berg T, Learned-Miller E (2008) Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In: Workshop on faces in \u2018Real-Life\u2019 Images: detection, alignment, and recognition"},{"key":"13917_CR14","doi-asserted-by":"crossref","unstructured":"Hukkel\u00e5s H, Mester R, Lindseth F (2019) Deepprivacy: A generative adversarial network for face anonymization. In: International symposium on visual computing, pp 565\u2013578","DOI":"10.1007\/978-3-030-33720-9_44"},{"issue":"13","key":"13917_CR15","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu Q, Ghanbari M (2008) Scope of validity of PSNR in image\/video quality assessment. Electronics Lett 44(13):800\u2013801","journal-title":"Electronics Lett"},{"key":"13917_CR16","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J, Zhou T, Efros A (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"13917_CR17","doi-asserted-by":"crossref","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of the European conference on computer vision, pp 694\u2013711","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"13917_CR18","doi-asserted-by":"crossref","unstructured":"Jourabloo A, Yin X, Liu X (2015) Attribute preserved face de-identification. In: 2015 international conference on biometrics, pp 278\u2013285","DOI":"10.1109\/ICB.2015.7139096"},{"key":"13917_CR19","first-page":"1755","volume":"10","author":"D King","year":"2009","unstructured":"King D (2009) Dlib-ml: A machine learning toolkit. J Mach Learn Res 10:1755\u20131758","journal-title":"J Mach Learn Res"},{"key":"13917_CR20","doi-asserted-by":"crossref","unstructured":"Liu Z, Luo P, Wang X, Tang X (2015) Deep learning face attributes in the wild. In: Proceedings of the IEEE international conference on computer vision, pp 3730\u20133738","DOI":"10.1109\/ICCV.2015.425"},{"key":"13917_CR21","doi-asserted-by":"crossref","unstructured":"Liu Z, Qi X, Torr P (2020) Global texture enhancement for fake face detection in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8060\u20138069","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"13917_CR22","unstructured":"Ma T, Li D, Wang W, Dong J (2021) CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation. arXiv:2105.11137"},{"key":"13917_CR23","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2794\u20132802","DOI":"10.1109\/ICCV.2017.304"},{"key":"13917_CR24","doi-asserted-by":"crossref","unstructured":"Maximov M, Elezi I, Leal-Taix\u00e9 L (2020) Ciagan: Conditional identity anonymization generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5447\u20135456","DOI":"10.1109\/CVPR42600.2020.00549"},{"key":"13917_CR25","doi-asserted-by":"crossref","unstructured":"Meden B, Emersic Z, Struc V, Peer P (2017) K-same-net: Neural-network-based face deidentification. In: 2017 international conference and workshop on bioinspired intelligence, pp 1\u20137","DOI":"10.1109\/IWOBI.2017.7985521"},{"issue":"9","key":"13917_CR26","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1049\/iet-spr.2017.0049","volume":"11","author":"B Meden","year":"2017","unstructured":"Meden B, Mall\u0131 RC, Fabijan S, Ekenel HK, \u0160truc V, Peer P (2017) Face deidentification with generative deep neural networks. IET Signal Process 11(9):1046\u20131054","journal-title":"IET Signal Process"},{"key":"13917_CR27","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784"},{"key":"13917_CR28","doi-asserted-by":"crossref","unstructured":"Najibi M, Samangouei P, Chellappa R, Davis LS (2017) Ssh: Single stage headless face detector. In: Proceedings of the IEEE international conference on computer vision, pp 4875\u20134884","DOI":"10.1109\/ICCV.2017.522"},{"issue":"1","key":"13917_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1143518.1143519","volume":"13","author":"C Neustaedter","year":"2006","unstructured":"Neustaedter C, Greenberg S, Boyle M (2006) Blur filtration fails to preserve privacy for home-based video conferencing. ACM Transactions on Computer-Human Interaction 13(1):1\u201336","journal-title":"ACM Transactions on Computer-Human Interaction"},{"issue":"2","key":"13917_CR30","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1109\/TKDE.2005.32","volume":"17","author":"EM Newton","year":"2005","unstructured":"Newton EM, Sweeney L, Malin B (2005) Preserving privacy by de-identifying face images. IEEE Trans Knowl Data Eng 17(2):232\u2013243","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"13917_CR31","unstructured":"Pang Z, Guo J, Ma Z, Sun W, Xiao Y (2021) Median stable clustering and global distance classification for cross-domain person re-identification. IEEE Trans Circuits Syst Video Technol, pp 1\u201315"},{"key":"13917_CR32","doi-asserted-by":"crossref","unstructured":"Pang Z, Guo J, Sun W, Xiao Y, Yu M (2021) Cross-domain person re-identification by hybrid supervised and unsupervised learning. Appl Intell, pp 1\u201315","DOI":"10.1007\/s10489-021-02551-8"},{"key":"13917_CR33","doi-asserted-by":"crossref","unstructured":"Panis G, Lanitis A (2014) An overview of research activities in facial age estimation using the FG-NET aging database. In: Proceedings of the European conference on computer vision, pp 737\u2013750","DOI":"10.1007\/978-3-319-16181-5_56"},{"key":"13917_CR34","doi-asserted-by":"crossref","unstructured":"Park T, Liu M, Wang T, Zhu JY (2019) Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2337\u20132346","DOI":"10.1109\/CVPR.2019.00244"},{"key":"13917_CR35","doi-asserted-by":"crossref","unstructured":"Ren Z, Lee Y, Ryoo M (2018) Learning to anonymize faces for privacy preserving action detection. In: Proceedings of the European conference on computer vision, pp 620\u2013636","DOI":"10.1007\/978-3-030-01246-5_38"},{"key":"13917_CR36","doi-asserted-by":"crossref","unstructured":"Ryoo MS, Kim K, Yang HJ (2018) Extreme low resolution activity recognition with multi-siamese embedding learning. In: Proceedings of AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12299"},{"key":"13917_CR37","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"13917_CR38","unstructured":"Shan S, Wenger E, Zhang J, Li H, Zheng H, Zhao BY (2020) Fawkes: Protecting privacy against unauthorized deep learning models. In: 29th Security Symposium, pp 1589\u20131604"},{"key":"13917_CR39","doi-asserted-by":"crossref","unstructured":"Sun Q, Ma L, Oh SJ, Van Gool L, Schiele B, Fritz M (2018) Natural and effective obfuscation by head inpainting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5050\u20135059","DOI":"10.1109\/CVPR.2018.00530"},{"key":"13917_CR40","doi-asserted-by":"crossref","unstructured":"Sun C, Shrivastava A, Singh S, Gupta A (2017) Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE international conference on computer vision, pp 843\u2013852","DOI":"10.1109\/ICCV.2017.97"},{"issue":"05","key":"13917_CR41","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1142\/S0218488502001648","volume":"10","author":"L Sweeney","year":"2002","unstructured":"Sweeney L (2002) k-anonymity: A model for protecting privacy. Internat J Uncertain Fuzziness Knowledge-Based Systems 10(05):557\u2013570","journal-title":"Internat J Uncertain Fuzziness Knowledge-Based Systems"},{"key":"13917_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of AAAI conference on artificial intelligence, pp 4278\u20134284","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"13917_CR43","unstructured":"Targ S, Almeida D, Lyman K (2016) Resnet in resnet: Generalizing residual architectures. arXiv:1603.080291603.08029"},{"key":"13917_CR44","doi-asserted-by":"crossref","unstructured":"Te G, Liu Y, Hu W, Shi H, Mei T (2020) Edge-aware graph representation learning and reasoning for face parsing. In: European conference on computer vision, pp 258\u2013274","DOI":"10.1007\/978-3-030-58610-2_16"},{"key":"13917_CR45","doi-asserted-by":"crossref","unstructured":"Wang Z, Simoncelli E, Bovik A (2003) Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems and Computers, vol 2, pp 1398\u20131402","DOI":"10.1109\/ACSSC.2003.1292216"},{"issue":"2","key":"13917_CR46","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s11263-018-1097-z","volume":"127","author":"Y Wu","year":"2019","unstructured":"Wu Y, Ji Q (2019) Facial landmark detection: A literature survey. Int J Comput Vis 127(2):115\u2013142","journal-title":"Int J Comput Vis"},{"issue":"1","key":"13917_CR47","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s11390-019-1898-8","volume":"34","author":"Y Wu","year":"2019","unstructured":"Wu Y, Yang F, Xu Y, Ling H (2019) Privacy-protective-GAN for privacy prerving face de-identification. J Comput Sci Technol 34(1):47\u201360","journal-title":"J Comput Sci Technol"},{"key":"13917_CR48","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy C, Tang X (2016) Wider face: a face detection benchmark. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5525\u20135533","DOI":"10.1109\/CVPR.2016.596"},{"key":"13917_CR49","doi-asserted-by":"crossref","unstructured":"Yang C, Xu Y, Shi J, Dai B, Zhou B (2020) Temporal pyramid network for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 591\u2013600","DOI":"10.1109\/CVPR42600.2020.00067"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13917-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13917-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13917-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T11:38:30Z","timestamp":1679657910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13917-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,7]]},"references-count":49,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["13917"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13917-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,7]]},"assertion":[{"value":"7 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We wish to confirm that there are no known conflicts of interest associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}