Deep Learning Technology for Identifying a Person of Interest in Real World

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 915)


In this paper, we will propose a new embedded system prototype called PubFace, which uses the CNN model trained from scratch on facial celebrity images [1], to identify a “Person of Interest” in public space. This is done by tuning this model on new dataset comprising 5000 real images of 1000 different identity collected from social networks as Facebook and Instagram. After I got permission of collected images persons to use their facial images in this scientific research project. Then, we have investigated some ways for compressing the number of parameters of the resulting model to reduce the memory needed for both storing and performing a forward pass while simultaneously preserving acceptable good accuracy.


Face recognition Artificial intelligence Deep learning Person of interest 


  1. 1.
    Ouanan, H., Ouanan, M., Aksasse, B.: Face recognition using deep features. Lect. Notes Netw. Syst. 25, 78–85 (2017)CrossRefGoogle Scholar
  2. 2.
    Ouanan, H., Ouanan, M., Aksasse, B.: Non-linear dictionary representation of deep features for face recognition from a single sample per person. Procedia Comput. Sci. 127, 114–122 (2018)CrossRefGoogle Scholar
  3. 3.
    Masakazu, M., Mori, K., Mitari, Y., Kaneda, Y.: Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Netw. 5, 555–559 (2003)Google Scholar
  4. 4.
    Portugal, I., Alencar, P., Cowan, D.: The use of machine learning algorithms in recommender systems: a systematic review. Expert Syst. Appl. (2017)Google Scholar
  5. 5.
    Yaniv, T., Ming, Y., Marc’Aurelio, R., Lior, W.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708. (2014)Google Scholar
  6. 6.
    Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments, University of Massachusetts, Amherst, Technical Report, pp. 07–49. (2007)Google Scholar
  7. 7.
    Sun, Y., Liang, D., Wang, X., Tang, X.: Deepid3: face recognition with very deep neural networks, arXiv preprint arXiv:1502.00873 (2015)
  8. 8.
    Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923. (2014)
  9. 9.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  10. 10.
    Han, S., Mao, H., Dally, W.J.: eep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)
  11. 11.
    Lin, D., Talathi, S., Annapureddy, S.: Fixed point quantization of deep convolutional networks. In: International Conference on Machine Learning, pp. 2849–2858. (2016)Google Scholar
  12. 12.
    OpenCV.: [Online]. Available: Accessed 30 April 2018
  13. 13.
    Raspberry Pi Foundation: Raspberry Pi Camera Module Product Page. URL: Accessed 24 Mar 2018
  14. 14.
    Keras: The Python Deep Learning library. [Online]. Available: 30 April 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science, ASIA Team, M2I Laboratory, Faculty of Science and TechniquesMoulay Ismail UniversityErrachidiaMorocco

Personalised recommendations