Face age synthesis: A review on datasets, methods, and open research areas
Pattern Recognition, vol.143, 2023 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 143
- Publication Date: 2023
- Doi Number: 10.1016/j.patcog.2023.109791
- Journal Name: Pattern Recognition
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, BIOSIS, Compendex, Computer & Applied Sciences, INSPEC, MLA - Modern Language Association Database, zbMATH
- Keywords: Age progression, Age regression, Face aging, GANs
- Yıldız Technical University Affiliated: Yes
Abstract
Face age synthesis is the determination of how a person looks in the future or the past by reconstructing their facial image. Determining the change in the human face over the years is a critical process for cross-age face recognition systems in forensic issues such as finding missing people and fugitive criminals. Therefore, it is a subject that has attracted attention in recent years. With the implementation of deep learning methods, better quality and photo-realistic images began to be produced. However, researchers continue to improve both aging accuracy and identity preservation requirements. We group the studies in the literature under two categories: classical methods and deep learning methods. We review both categories in the methods used, evaluation methods, and databases.