{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:53:06Z","timestamp":1777503186430,"version":"3.51.4"},"reference-count":18,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T00:00:00Z","timestamp":1746748800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Currently, predicting a person\u2019s facial appearance many years later based on early facial features remains a core technical challenge. In this paper, we propose a cross-age face prediction framework based on Generative Adversarial Networks (GANs). This framework extracts key features from early photos of the target individual and predicts their facial appearance at different ages in the future. Within our framework, we designed a GAN-based image restoration algorithm to enhance image deblurring capabilities and improve the generation of fine details, thereby increasing image resolution. Additionally, we introduced a semi-supervised learning algorithm called Multi-scale Feature Aggregation Scratch Repair (Semi-MSFA), which leverages both synthetic datasets and real historical photos to better adapt to the task of restoring old photographs. Furthermore, we developed a generative adversarial network incorporating a self-attention mechanism to predict age-progressed face images, ensuring the generated images maintain relatively stable personal characteristics across different ages. To validate the robustness and accuracy of our proposed framework, we conducted qualitative and quantitative analyses on open-source portrait databases and volunteer-provided data. Experimental results demonstrate that our framework achieves high prediction accuracy and strong generalization capabilities.<\/jats:p>","DOI":"10.1371\/journal.pone.0322280","type":"journal-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:38:22Z","timestamp":1746812302000},"page":"e0322280","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["A research on cross-age facial recognition technology based on AT-GAN"],"prefix":"10.1371","volume":"20","author":[{"given":"Guangxuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0202-7215","authenticated-orcid":true,"given":"Xingyuan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,5,9]]},"reference":[{"issue":"02","key":"pone.0322280.ref001","first-page":"193","article-title":"Age changes in cephalofacial morphological features of Han Chinese in Jiangxi","volume":"31","author":"Y. Li","year":"2012","journal-title":"J Anthropol"},{"issue":"4","key":"pone.0322280.ref002","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/TIFS.2009.2038751","article-title":"Face verification across age progression using discriminative methods.","volume":"5","author":"H. Ling","year":"2010","journal-title":"IEEE Transactions on Information Forensics and Security"},{"issue":"1","key":"pone.0322280.ref003","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/TPAMI.2020.3011426","article-title":"Towards age-invariant face recognition","volume":"44","author":"J Zhao","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"pone.0322280.ref004","first-page":"304","article-title":"Cross-age face synthesis based on conditional adversarial autoencoder","volume":"48","author":"Z. Cheng","year":"2022","journal-title":"Computer Eng"},{"issue":"6","key":"pone.0322280.ref005","first-page":"137","article-title":"Generative adversarial networks","volume":"57","author":"I. Goodfellow","year":"2014","journal-title":"Communications of the ACM"},{"key":"pone.0322280.ref006","article-title":"Improved Techniques for Training GANs.","volume-title":"Neural Information Processing Systems","author":"T. Salimans","year":"2016"},{"key":"pone.0322280.ref007","article-title":"Geometric GAN","author":"JH. Lim","year":"2017","journal-title":"arXiv.org"},{"issue":"1","key":"pone.0322280.ref008","first-page":"1","article-title":"An overview of digital image restoration techniques","volume":"12","author":"H. Zhang","year":"2007","journal-title":"Chinese Journal of Image Graphics"},{"key":"pone.0322280.ref009","first-page":"1724","article-title":"Pik-Fix: Restoring and Colorizing Old Photos.","volume-title":"IEEE Workshop\/Winter Conference on Applications of Computer Vision","author":"R. 9Xu","year":"2022"},{"key":"pone.0322280.ref010","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","article-title":"Neural mechanisms of selective visual attention","volume":"18","author":"R Desimone","year":"1995","journal-title":"Annu Rev Neurosci"},{"key":"pone.0322280.ref011","article-title":"Towards understanding the effectiveness of attention mechanism.","author":"X. Ye","year":"2021","journal-title":"arXiv.org"},{"issue":"2","key":"pone.0322280.ref012","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1049\/iet-bmt.2014.0053","article-title":"Overview of research on facial ageing using the FG-NET ageing database","volume":"5","author":"G Panis","year":"2016","journal-title":"IET Biometrics"},{"issue":"24","key":"pone.0322280.ref013","first-page":"27","article-title":"Research progress on cross-age face recognition based on aging model","volume":"57","author":"J Li","year":"2021","journal-title":"Computer Eng Appl"},{"key":"pone.0322280.ref014","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58539-6_44","article-title":"Lifespan Age Transformation Synthesis.","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R. Or-El","year":"2020"},{"key":"pone.0322280.ref015","unstructured":"Hasan M.; Nishat N. et al. A journal of innovative technology and exploring engineering. 2024"},{"issue":"10","key":"pone.0322280.ref016","first-page":"245","article-title":"Scratch repair of old photos based on multi-scale attention semi-supervised learning","volume":"48","author":"W. Gao","year":"2022","journal-title":"Computer Eng"},{"issue":"03","key":"pone.0322280.ref017","first-page":"321","article-title":"Research progress and prospect of generative adversarial network GAN","volume":"43","author":"K. Wang","year":"2017","journal-title":"J Automation"},{"issue":"8","key":"pone.0322280.ref018","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1109\/TCSVT.2020.3037179","article-title":"Attention-aligned network for person re-identification","volume":"31","author":"S Lian","year":"2021","journal-title":"IEEE Trans Circuits Syst Video Technol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:38:34Z","timestamp":1746812314000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322280"}},"subtitle":[],"editor":[{"given":"Zeeshan","family":"Ahmad","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,9]]},"references-count":18,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0322280","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,9]]}}}