Advertisement

Age and Gender Estimation of Asian Faces Using Deep Residual Network

  • Hoang Nguyen
  • Hieu Trung HuynhEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11814)

Abstract

In recent years, with the rise of deep learning and computer vision, researchers have been looking deeply into the age and gender estimation problem due to its practical influences. A lot of fields, from insurance, retails to marketing, could benefit tremendously from the presence of a reliable estimator, as it would allow companies to easily identify their customer demographics. A great number of models have been proposed, and they have achieved remarkable results. However, because of the lack of open-source, multiethnic dataset, most modern Age and Gender estimating model are trained solely based on white people with Western facial features, and thus fall short with non-Caucasian people. Therefore, in this paper, using a newly-improved Asian face database, we developed an applicable Wide ResNet model to predict the age and the gender of a person using just one image, assuming he/she comes from an Asian background. The model has shown some promising results, as it can match the performance of Microsoft’s how-old API estimator in a specific dataset.

Keywords

Deep Learning Convolutional Neural Network ResNet Wide ResNet Age and Gender estimation 

Notes

Acknowledgement

This work was supported by the Ho Chi Minh city Department of Science and Technology [grant numbers 1131/QD-SKHCN, 06/2018/HD-QKHCN].

References

  1. 1.
    Dietz, M.: Understand deep residual networks–a simple, modular learning framework that has redefined state-of-the-art (2017). https://blog.waya.ai/deep-residual-learning-9610bb62c355
  2. 2.
    Hayashi, J., Koshimizu, H., Hata, S.: Age and gender estimation based on facial image analysis. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS (LNAI), vol. 2774, pp. 863–869. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-45226-3_118CrossRefGoogle Scholar
  3. 3.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. CoRR abs/1502.01852 (2015). http://arxiv.org/abs/1502.01852
  4. 4.
    Ku, C.-L., Chiou, C.-H., Gao, Z.-Y., Tsai, Y.-J., Fuh, C.-S.: Age and gender estimation using multiple-image features. In: Sun, Z., Shan, S., Yang, G., Zhou, J., Wang, Y., Yin, Y.L. (eds.) CCBR 2013. LNCS, vol. 8232, pp. 441–448. Springer, Cham (2013).  https://doi.org/10.1007/978-3-319-02961-0_55CrossRefGoogle Scholar
  5. 5.
    Rothe, R., Timofte, R., Gool, L.V.: DEX: deep expectation of apparent age from a single image. In: EEE International Conference on Computer Vision Workshops (ICCVW), December 2015Google Scholar
  6. 6.
    Rothe, R., Timofte, R., Gool, L.V.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. (IJCV) 126, 144–157 (2018)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. CoRR abs/1605.07146 (2016). http://arxiv.org/abs/1605.07146
  8. 8.
    Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. CoRR abs/1710.09412 (2017). http://arxiv.org/abs/1710.09412
  9. 9.
    Zhang, Y., Liu, L., Li, C., Loy, C.C.: Quantifying facial age by posterior of age comparisons (2017)Google Scholar
  10. 10.
    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. CoRR abs/1708.04896 (2017). http://arxiv.org/abs/1708.04896

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Vietnamese-German UniversityThu Dau MotVietnam
  2. 2.Industrial University of Ho Chi Minh CityHo Chi Minh CityVietnam

Personalised recommendations