{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:20:27Z","timestamp":1769822427350,"version":"3.49.0"},"reference-count":40,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T00:00:00Z","timestamp":1691625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"MSIT (Ministry of Science and ICT), Korea","doi-asserted-by":"publisher","award":["IITP-2023-2020-0-01462"],"award-info":[{"award-number":["IITP-2023-2020-0-01462"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"MSIT (Ministry of Science and ICT), Korea","doi-asserted-by":"publisher","award":["2023R1A2C1006944"],"award-info":[{"award-number":["2023R1A2C1006944"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Research Foundation of Korea (NRF)","award":["IITP-2023-2020-0-01462"],"award-info":[{"award-number":["IITP-2023-2020-0-01462"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["2023R1A2C1006944"],"award-info":[{"award-number":["2023R1A2C1006944"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep-learning-based image inpainting methods have made remarkable advancements, particularly in object removal tasks. The removal of face masks has gained significant attention, especially in the wake of the COVID-19 pandemic, and while numerous methods have successfully addressed the removal of small objects, removing large and complex masks from faces remains demanding. This paper presents a novel two-stage network for unmasking faces considering the intricate facial features typically concealed by masks, such as noses, mouths, and chins. Additionally, the scarcity of paired datasets comprising masked and unmasked face images poses an additional challenge. In the first stage of our proposed model, we employ an autoencoder-based network for binary segmentation of the face mask. Subsequently, in the second stage, we introduce a generative adversarial network (GAN)-based network enhanced with attention and Masked\u2013Unmasked Region Fusion (MURF) mechanisms to focus on the masked region. Our network generates realistic and accurate unmasked faces that resemble the original faces. We train our model on paired unmasked and masked face images sourced from CelebA, a large public dataset, and evaluate its performance on multi-scale masked faces. The experimental results illustrate that the proposed method surpasses the current state-of-the-art techniques in both qualitative and quantitative metrics. It achieves a Peak Signal-to-Noise Ratio (PSNR) improvement of 4.18 dB over the second-best method, with the PSNR reaching 30.96. Additionally, it exhibits a 1% increase in the Structural Similarity Index Measure (SSIM), achieving a value of 0.95.<\/jats:p>","DOI":"10.3390\/s23167094","type":"journal-article","created":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T10:52:40Z","timestamp":1691664760000},"page":"7094","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["GANMasker: A Two-Stage Generative Adversarial Network for High-Quality Face Mask Removal"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-8969","authenticated-orcid":false,"given":"Mohamed","family":"Mahmoud","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea"},{"name":"Information Technology Department, Faculty of Computers and Information, Assiut University, Assiut 71515, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4333-2852","authenticated-orcid":false,"given":"Hyun-Soo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,10]]},"reference":[{"key":"ref_1","unstructured":"Jassim, F.A. (2013). Image inpainting by Kriging interpolation technique. arXiv."},{"key":"ref_2","first-page":"91","article-title":"Medical image inpainting with RBF interpolation technique","volume":"7","author":"Alsalamah","year":"2016","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TIP.2004.833105","article-title":"Region filling and object removal by exemplar-based image inpainting","volume":"13","author":"Criminisi","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., and Goldman, D.B. (2009). PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph., 28.","DOI":"10.1145\/1576246.1531330"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1109\/TPAMI.2012.39","article-title":"Tensor completion for estimating missing values in visual data","volume":"35","author":"Liu","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Simakov, D., Caspi, Y., Shechtman, E., and Irani, M. (2008, January 23\u201328). Summarizing visual data using bidirectional similarity. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587842"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2185520.2185578","article-title":"Image melding: Combining inconsistent images using patch-based synthesis","volume":"31","author":"Darabi","year":"2012","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bertalmio, M., Sapiro, G., Caselles, V., and Ballester, C. (2000, January 23\u201328). Image inpainting. Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","DOI":"10.1145\/344779.344972"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Prasath, V.S., Thanh, D.N., Hai, N.H., and Cuong, N.X. (2017, January 7\u20138). Image restoration with total variation and iterative regularization parameter estimation. Proceedings of the 8th International Symposium on Information and Communication Technology, Nha Trang, Vietnam.","DOI":"10.1145\/3155133.3155191"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s12046-013-0152-2","article-title":"A novel image inpainting technique based on median diffusion","volume":"38","author":"Biradar","year":"2013","journal-title":"Sadhana"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27\u201330). Context encoders: Feature learning by inpainting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073659","article-title":"Globally and locally consistent image completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"ref_13","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., and Huang, T.S. (November, January 27). Free-form image inpainting with gated convolution. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_14","unstructured":"Nazeri, K., Ng, E., Joseph, T., Qureshi, F.Z., and Ebrahimi, M. (2019). Edgeconnect: Generative image inpainting with adversarial edge learning. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.C., Tao, A., and Catanzaro, B. (2018, January 8\u201314). Image inpainting for irregular holes using partial convolutions. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, S., Yang, J., and Yang, M.H. (2017, January 21\u201326). Generative face completion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.624"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Khan, M.K.J., Ud Din, N., Bae, S., and Yi, J. (2019). Interactive removal of microphone object in facial images. Electronics, 8.","DOI":"10.3390\/electronics8101115"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"44276","DOI":"10.1109\/ACCESS.2020.2977386","article-title":"A novel GAN-based network for unmasking of masked face","volume":"8","author":"Din","year":"2020","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jam, J., Kendrick, C., Drouard, V., Walker, K., Hsu, G.S., and Yap, M.H. (2021, January 5\u20139). R-mnet: A perceptual adversarial network for image inpainting. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Virtual Event.","DOI":"10.1109\/WACV48630.2021.00276"},{"key":"ref_20","unstructured":"Kasem, M., Abdallah, A., Berendeyev, A., Elkady, E., Abdalla, M., Mahmoud, M., Hamada, M., Nurseitov, D., and Taj-Eddin, I. (2022). Deep learning for table detection and structure recognition: A survey. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.neucom.2021.11.101","article-title":"Tncr: Table net detection and classification dataset","volume":"473","author":"Abdallah","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ibrahem, H., Salem, A., and Kang, H.S. (2022). Exploration of Semantic Label Decomposition and Dataset Size in Semantic Indoor Scenes Synthesis via Optimized Residual Generative Adversarial Networks. Sensors, 22.","DOI":"10.3390\/s22218306"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hamada, M.A., Abdallah, A., Kasem, M., and Abokhalil, M. (2021, January 28\u201330). Neural network estimation model to optimize timing and schedule of software projects. Proceedings of the 2021 IEEE International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan.","DOI":"10.1109\/SIST50301.2021.9465887"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mahmoud, M., Kasem, M., Abdallah, A., and Kang, H.S. (2022, January 26\u201328). AE-LSTM: Autoencoder with LSTM-Based Intrusion Detection in IoT. Proceedings of the 2022 International Telecommunications Conference (ITC-Egypt), Alexandria, Egypt.","DOI":"10.1109\/ITC-Egypt55520.2022.9855688"},{"key":"ref_25","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, 5\u20139 October 2015, Proceedings, Part III 18, Springer."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_27","unstructured":"Liu, Z., Luo, P., Wang, X., and Tang, X. (2018). Large-scale celebfaces attributes (celeba) dataset. Retrieved August, 15."},{"key":"ref_28","unstructured":"Anwar, A., and Raychowdhury, A. (2020). Masked face recognition for secure authentication. arXiv."},{"key":"ref_29","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv."},{"key":"ref_30","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_31","unstructured":"Johnson, J., Alahi, A., and Fei-Fei, L. (2016). Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11\u201314 October 2016, Proceedings, Part II 14, Springer."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., and Paul Smolley, S. (2017, January 22\u201329). Least squares generative adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_35","unstructured":"LynnHo (2023, March 21). HD-CelebA-Cropper. Available online: https:\/\/github.com\/LynnHo\/HD-CelebA-Cropper.git."},{"key":"ref_36","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst., 32."},{"key":"ref_37","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind\u201d image quality analyzer","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_40","unstructured":"Chen, C., and Mo, J. (2023, June 10). IQA-PyTorch: PyTorch Toolbox for Image Quality Assessment. Available online: https:\/\/github.com\/chaofengc\/IQA-PyTorch."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7094\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:30:50Z","timestamp":1760128250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,10]]},"references-count":40,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["s23167094"],"URL":"https:\/\/doi.org\/10.3390\/s23167094","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,10]]}}}