Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194537,
        author = {Ms.K.Sravani and Appala Sai Krishna and Burugu Sri Karun Reddy and Bachhu Harish and Kolanu Chandana},
        title = {Face Age Synthesis Using Generative Adversarial Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6621-6625},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194537},
        abstract = {This project presents a novel approach to face age synthesis and age- invariant face recognition through a unified deep learning framework named MTLFace. The system simultaneously performs realistic facial aging and robust identity preservation across age gaps using GANs. By integrating attention-based feature decomposition and identity-conditioned modules, the model effectively disentangles age-related and identity-specific features. A selective fine-tuning mechanism refines recognition accuracy using only high- quality synthetic images. The approach is validated on largescale, annotated datasets and shows superior performance in both visual realism and recognition accuracy, with potential applications in forensics and missing person identification.},
        keywords = {Generative Adversarial Networks (GANs), Age-Invariant Face Recognition, Forensics Applications, Image Quality Filtering, Fine-grained Age Transformation, AR/VR Integration, Ethical AI, Attention Feature Decomposition (AFD), Identity Conditional Module (ICM)},
        month = {March},
        }