ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Robust Deep Age Estimation Method Using Artificially Generated Image Set

  • Jang, Jaeyoon (SW & Content Research Loboratory, ETRI, Department of Computer Software Engineering, University of Science and Technology) ;
  • Jeon, Seung-Hyuk (SNOW) ;
  • Kim, Jaehong (SW & Content Research Loboratory, ETRI) ;
  • Yoon, Hosub (SW & Content Research Loboratory, ETRI, Department of Computer Software Engineering, University of Science and Technology)
  • Received : 2017.02.01
  • Accepted : 2017.06.19
  • Published : 2017.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

Keywords

References

  1. T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, 2002, pp. 971-987. https://doi.org/10.1109/TPAMI.2002.1017623
  2. Z. Yang and H. Ai, "Demographic Classification with Local Binary Patterns," Int. Conf. Biometrics, Crystal City, VA, USA, 27-30, Sept. 2007, pp. 464-473.
  3. F. Gao and H. Ai, "Face Age Classification on Consumer Images with Gabor Feature and Fuzzy Lda Method," Int. Conf. Biometrics, Alghero, Italy, 2-5, June 2009, pp. 132-141.
  4. J.-D. Txia and C.-L. Huang, "Age Estimation Using AAM and Local Facial Features," Int. Inform. Hiding Multimedia Signal Process., Kyoto, Japan, 12-14, Sept. 2009, pp. 885-888.
  5. G. Guo et al., "Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression," IEEE Trans. Image Process., vol. 17, no. 7, 2008, pp. 1178-1188. https://doi.org/10.1109/TIP.2008.924280
  6. O.M. Parkhi, A. Vedaldi, and A. Zisserman, "Deep Face Recognition," British Mach. Vis. Conf., Swansea, UK, 7-10, Sept. 2015.
  7. G. Guo and G. Mu, "Simultaneous Dimensionality Reduction and Human Age Estimation Via Kernel Partial Least Squares Regression," IEEE Conf. Comput. Vis. Pattern Recogn., Colorado Springs, CO, USA, 20-25 June 2011, pp. 657-664.
  8. Y. Fu and T.S. Huang, "Human Age Estimation with Regression on Discriminative Aging Manifold," IEEE Trans. Multimedia, vol. 10, no. 4, 2008, pp. 578-584. https://doi.org/10.1109/TMM.2008.921847
  9. G. Guo and G. Mu, "Joint Estimation of Age, Gender and Ethnicity: CCA vs. PLS," IEEE Int. Conf. Workshops Automatic Face Gesture Recogn., Shanghai, China, 22-26, Apr. 2013, pp. 1-6.
  10. Y. Dong, Y. Liu, and S. Lian, "Automatic Age Estimation Based on Deep Learning Algorithm," Neurocomput., vol. 187, 2016, pp. 4-10. https://doi.org/10.1016/j.neucom.2015.09.115
  11. J. Huang et al., "Age Classification With Deep Learning Face Representation," Multimedia Tools Applicat., vol. 76, no. 19, Oct. 2017, pp. 1-17. https://doi.org/10.1007/s11042-015-3011-9
  12. G. Antipov et al., "Apparent Age Estimation From Face Images Combining General and Children-Specialized Deep Learning Models," Proc. IEEE Conf. Comput. Vis. Pattern Recogn. Workshops, Las Vegas, NV, USA, 2016, pp. 801-809.
  13. Z. Niu et al., "Ordinal Regression with Multiple Output CNN for Age Estimation," Proc. IEEE Conf. Comput. Vis. Pattern Recogn., Las Vegas, NV, USA, 27-30, June 2016, pp. 4920-4928.
  14. F. Gurpinar et al., "Kernel ELM and CNN Based Facial Age Estimation," Proc. IEEE Conf. Comput. Vis. Pattern Recogn. Workshops, Las Vegas, NV, USA, 2016, pp. 785-791.
  15. J.-J. Lv et al., "Data Augmentation for Face Recognition," Nerocomput., vol. 230, 2017, pp. 184-196. https://doi.org/10.1016/j.neucom.2016.12.025
  16. Y. Nirkin et al., "On Face Segmentation, Face Swapping, and Face Perception," arXiv preprint arXiv:1704.06729, 2017.
  17. D. Kim et al., "Deep 3D Face Identification," arXiv preprint arXiv:1703.10714, 2017.
  18. P.J. Phillips et al., "Overview of the Face Recognition Grand Challenge," In IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn., San Diego, CA, SUA, 20-25 June 2005, pp. 947-954.
  19. K. Ricanek and T. Tesafaye, "Morph: A Longitudinal Image Database of Normal Adult Age-Progression," In Int. Conf. Automatic Face Gesture Recogn., Southampton, UK, 10-12, Apr. 2006, pp. 341-345.
  20. B. Ni, Z. Song, and S. Yan, "Web Image Mining Towards Universal Age Estimator," In Proc. ACM Int. Conf. Multimedia, Beijing, China, 19-24, Oct. 2009, pp. 85-94.
  21. E. Eidinger, R. Enbar, and T. Hassner, "Age and Gender Estimation of Unfiltered Faces, Information Forensics and Security," IEEE Trans. Inform. Foren. Secur., vol. 9, no. 12, Dec. 2014, pp. 2170-2179. https://doi.org/10.1109/TIFS.2014.2359646
  22. R. Rothe, R. Timofte, and L. Gool, "DEX: Deep Expectation of Apparent Age From a Single Image," IEEE Int. Conf. Comput. Vis. Workshop, Santiago, Chile, 7-13, Dec. 2015, pp. 10-15.
  23. X. Baro et al., "Chalearn Looking at People Challenge 2015: Dataset and Results," CVPR, ChaLearn Looking at People Workshop, 2015.
  24. D.E. King, "Dlib-ml: A Machine Learning Toolkit," J. Mach. Learn. Res. vol. 10, July 2009, pp. 1755-1758.
  25. V. Kazemi and J. Sullivan, "One Millisecond Face Alignment with An Ensemble of Regression Trees," IEEE Conf. Comput. Vis. Pattern Recogn., Columbus, OH, USA, 23-28, June 2014, pp. 1867-1874.
  26. C. Sagonas et al., "300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge," IEEE Int. Conf. Comput. Vis. Workshops, Sydney, Australia, 2-8 Dec. 2013, pp. 397-403.
  27. C. Sagonas et al., "A Semi-Automatic Methodology for Facial Landmark Annotation," IEEE Conf. Comput. Vis. Pattern Recogn. Workshops, Portland, OR, USA, 23-28, June 2013, pp. 896-903.
  28. J. Saragih and R. Gocke, "Learning AAM Fitting Through Simulation," Pattern Recogn., vol. 42, no. 11, 2009, pp. 2628-2636. https://doi.org/10.1016/j.patcog.2009.04.014
  29. G. Mu et al., "Human Age Estimation Using Bio-Inspired Features," IEEE Conf. Comput. Vis. Pattern Recogn., Miami, FL, USA, 20-25, June 2009, pp. 112-119.
  30. J. Qiu et al., "Hierarchical Aggregation Based Deep Aging Feature for Age Prediction," Int. Conf. Digital Image Comput.: Tech. Applicat., Adelaide, Australia, 23-25, Nov. 2015, pp. 1-5.
  31. K.-Y. Chang, C.-S. Chen, and Y.-P. Hung, "Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation," IEEE, Conf. Comput. Vis. Pattern Recogn., Colorado Springs, CO, USA, 20-25, June 2011, pp. 585-592.
  32. L. Gil and T. Hassner, "Age and Gender Classification Using Convolutional Neural Networks," IEEE Conf. Comput. Vis. Pattern Recogn. Workshops., Boston, MA, USA, 7-12, June 2015pp. 34-42.
  33. J.-C. Chen et al., "A Cascaded Convolutional Neural Network for Age Estimation of Unconstrained Faces," IEEE Int. Conf. Biometrics Theory, Applicat. Syst., Niagara Falls, NY, USA, 6-9 Sept. 2016, pp. 1-8.

Cited by

  1. An Energy-Efficient Method for Human Activity Recognition with Segment-Level Change Detection and Deep Learning vol.19, pp.17, 2017, https://doi.org/10.3390/s19173688
  2. Real-Time Hair Segmentation Using Mobile-Unet vol.10, pp.2, 2021, https://doi.org/10.3390/electronics10020099
  3. Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection vol.10, pp.2, 2017, https://doi.org/10.3390/electronics10020167