Fusion of Active Appearance Model and Histogram of Oriented Gradient for Age Estimation

  • Authors

    • Quan Yan Chang
    • Thian Song Ong
    • Siew Chin Chong
    2018-11-26
    https://doi.org/10.14419/ijet.v7i4.29.21849
  • AAM, AGE ESTIMATION, FACE RECOGNITION, HOG

  • In recent years, automated age estimation through face images has attracted the interest among the research due to its variety applications in law enforcement, human computer interaction etc. This paper presents the fusion of Active Appearances Model (AAM) with Histogram of Oriented Gradients (HOG) to form the face descriptors for automatic age estimation. AAM and HOG are known to be reliable feature extraction techniques for shape and texture images. The weaknesses of both are minimized and the strengths of both are utilized in the proposed method for better age estimation model. The proposed method is evaluated using two benchmarked age estimation datasets and promising results is generated.

  • References

    1. [1] Khoa Luu, Karl Ricanek, Tien D. Bui, and Ching Y. Suen. Age estimation using active appearance models and support vector machine regression. Third IEEE International Conference on Biometrics, pages 314-318, 2009.

      [2] Panis, G., & Lanitis, A. (2014, September). An overview of research activities in facial age estimation using the FG-NET aging database. In European Conference on Computer Vision (pp. 737-750). Springer International Publishing.

      [3] Narayanan Ramanathan, Rama Chellappa, and Soma Biswas. Age progression in human faces: A survey. Journal of Visual Languages and Computing, 2009.

      [4] T.F.Cootes, G.J. Edwards, and C.J.Taylor. Active appearance models. In Proc. European Conference on Computer Vision, 2:484{498, 1998.

      [5] Amrutha Sethuram, Eric Patterson, Karl Ricanek, and Allen Rawls. Improvements and performance evaluation concerning synthetic age progression and face recognition affected by adult aging. IEEE Transactions on Image Processing, 5558:62-71, 2009.

      [6] I.T. Jolliffe, Principal Component Analysis, second ed. Springer-Verlag, 2002.

      [7] Guo, Z., Zhang, L., Zhang, D., & Mou, X. (2010, September). Hierarchical multiscale LBP for face and palmprint recognition. In Image Processing (ICIP), 2010 17th IEEE International Conference on (pp. 4521-4524). IEEE.

      [8] Lindeberg, T. (2012). Scale invariant feature transform. Scholarpedia, 7(5), 10491.

      [9] FG-NET. Fg-net aging database.

      [10] A. M. Albert and K. Ricanek. The morph database: Investigating the effects of adult craniofacial aging on automated face-recognition technology. Forensic Science Communications, 10(2), 2008

      [11] Geng, X., Zhou, Z. H., & Smith-Miles, K. (2007). Automatic age estimation based on facial aging patterns. IEEE Transactions on pattern analysis and machine intelligence, 29(12), 2234-2240.

      [12] S. Yan, H. Wang, T. S. Huang, Q. Yang, and X. Tang. Ranking with uncertain labels. IEEE International Conference on Multimedia and Expo, pages 96{99, 2007.

      [13] Khoa Luu, Tien Dai Bui, and Ching Y. Suen. A tutorial on support vector regression. Statistics and Computing, 14(3):199{222, 1998.

      [14] X. Geng, K. Smith-Miles, and Z.-H. Zhou. Facial age estimation by nonlinear aging pattern subspace. 16th ACM International Conference on Multimedia, pages 721-724, 2008.

  • Downloads

  • How to Cite

    Chang, Q. Y., Ong, T. S., & Chong, S. C. (2018). Fusion of Active Appearance Model and Histogram of Oriented Gradient for Age Estimation. International Journal of Engineering & Technology, 7(4.29), 80-83. https://doi.org/10.14419/ijet.v7i4.29.21849