Face Aging using Generative Adversarial Network

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 12 | Issue : 01 | Page :
    By

    PVS Lakshmi Jagadamba,

  • Amrutha Gudimetla,

  • Srija Katru,

  • Pujitha Asapu,

  • Harshitha Kandregula,

  1. Professor and Head, Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (Autonomous) (GVP) (GVPCE), Visakhapatnam, Andhra Pradesh, India
  2. Student, Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (Autonomous) (GVP) (GVPCE), Visakhapatnam, Andhra Pradesh, India
  3. Student, Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (Autonomous) (GVP) (GVPCE), Visakhapatnam, Andhra Pradesh, India
  4. Student, Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (Autonomous) (GVP) (GVPCE), Visakhapatnam, Andhra Pradesh, India
  5. Student, Department of Computer Science and Engineering, Gayatri Vidya Parishad College of Engineering (Autonomous) (GVP) (GVPCE), Visakhapatnam, Andhra Pradesh, India

Abstract

This project addresses the challenge of predicting how a person may look in the future or how they appeared in the past using a single photograph. While existing methods mainly focus on altering texture, they often neglect changes in head shape that naturally occur during the aging process, limiting their effectiveness, especially when applied to images of children. To tackle this issue, a novel approach is introduced that employs a multi-domain image-to-image generative adversarial network architecture. This innovative framework captures a continuous bi-directional adversarial aging process in its learned latent space. By training our network on the FFHQ dataset, meticulously annotated for age, gender, and semantic segmentation, establishing fixed age classes as reference points to approximate seamless age transformation. Our model is capable of generating full head portraits spanning ages 0 to 70 from a single input photograph, encompassing both texture and head shape modifications. Through extensive experimentation across diverse datasets, it showcases substantial enhancements over existing techniques, underscoring the efficacy and versatility of our proposed methodology.

Keywords: head shape, single input photograph, bi-directional, semantic segmentation, efficacy.

[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]

How to cite this article:
PVS Lakshmi Jagadamba, Amrutha Gudimetla, Srija Katru, Pujitha Asapu, Harshitha Kandregula. Face Aging using Generative Adversarial Network. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(01):-.
How to cite this URL:
PVS Lakshmi Jagadamba, Amrutha Gudimetla, Srija Katru, Pujitha Asapu, Harshitha Kandregula. Face Aging using Generative Adversarial Network. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(01):-. Available from: https://journals.stmjournals.com/joipprp/article=2025/view=193108


References

  1. Antipov G, Baccouche M, Dugelay JL. Face aging with conditional generative adversarial networks. In2017 IEEE international conference on image processing (ICIP) 2017 Sep 17 (pp. 2089-2093). IEEE.
  2. He X, Chen T, Kan MY, Chen X. Trirank: Review-aware explainable recommendation by modeling aspects. In Proceedings of the 24th ACM international on conference on information and knowledge management 2015 Oct 17 (pp. 1661-1670).
  3. Kemelmacher-Shlizerman I, Suwajanakorn S, Seitz SM. Illumination-aware age progression. In Proceedings of the IEEE conference on computer vision and pattern recognition 2014 (pp. 3334-3341).
  4. Nhan Duong C, Gia Quach K, Luu K, Le N, Savvides M. Temporal non-volume preserving approach to facial age-progression and age-invariant face recognition. In Proceedings of the IEEE international conference on computer vision 2017 (pp. 3735-3743).
  5. Wang W, Yan Y, Cui Z, Feng J, Yan S, Sebe N. Recurrent face aging with hierarchical autoregressive memory. IEEE transactions on pattern analysis and machine intelligence. 2018 Feb 7;41(3):654-68.
  6. Wang W, Cui Z, Yan Y, Feng J, Yan S, Shu X, Sebe N. Recurrent face aging. In Proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 2378-2386).
  7. Tang J, Li Z, Lai H, Zhang L, Yan S. Personalized age progression with bi-level aging dictionary learning. IEEE transactions on pattern analysis and machine intelligence. 2017 May 17;40(4):905-17.
  8. Bando Y, Kuratate T, Nishita T. A simple method for modeling wrinkles on human skin. In10th Pacific Conference on Computer Graphics and Applications, 2002. Proceedings. 2002 Oct 9 (pp. 166-175). IEEE.
  9. Boissieux L, Kiss G, Thalmann NM, Kalra P. Simulation of skin aging and wrinkles with cosmetics insight. In Computer Animation and Simulation 2000: Proceedings of the Eurographics Workshop in Interlaken, Switzerland, August 21–22, 2000 2000 (pp. 15-27). Springer Vienna.
  10. Burt DM, Perrett DI. Perception of age in adult Caucasian male faces: computer graphic manipulation of shape and colour information. Proceedings of the Royal Society of London. Series B: Biological Sciences. 1995 Feb 22;259(1355):137-43.
  11. Chen BC, Chen CS, Hsu WH. Cross-age reference coding for age-invariant face recognition and retrieval. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13 2014 (pp. 768-783). Springer International Publishing.
  12. Chen LC. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587. 2017.
  13. Choi Y, Choi M, Kim M, Ha JW, Kim S, Choo J. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 8789-8797).
  14. Choi Y, Uh Y, Yoo J, Ha JW. Stargan v2: Diverse image synthesis for multiple domains. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2020 (pp. 8188-8197).
  15. Duong CN, Luu K, Quach KG, Bui TD. Longitudinal face aging in the wild-recent deep learning approaches. arXiv preprint arXiv:1802.08726. 2018 Feb 23.
  16. Fu Y, Guo G, Huang TS. Age synthesis and estimation via faces: A survey. IEEE transactions on pattern analysis and machine intelligence. 2010 Feb 5;32(11):1955-76.
  17. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).
  18. Huang X, Belongie S. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE international conference on computer vision 2017 (pp. 1501-1510).
  19. Huang X, Liu MY, Belongie S, Kautz J. Multimodal unsupervised image-to-image translation. In Proceedings of the European conference on computer vision (ECCV) 2018 (pp. 172-189).
  20. Isola P, Zhu JY, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 1125-1134).
Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 25/10/2024
Accepted 07/11/2024
Published 08/01/2025
251

Login


My IP

PlumX Metrics