access icon free Improved deep face identification with multi-class pairwise discriminant loss

A novel method to extract discriminative deep feature representations of facial images for face identification is presented. A new ‘multi-class pairwise discriminant loss’ is devised and incorporated it into the general deep convolutional neural network learning framework in a novel way, leading to highly discriminative deep face features. The method shows significant improvement over existing deep feature extraction techniques relying on softmax or triplet loss. Moreover, the method achieves a level of accuracy on the widely used identification protocols, which are better and comparable results than other state-of-the-art methods.

Inspec keywords: face recognition; learning (artificial intelligence); feature extraction; feedforward neural nets

Other keywords: facial images; multiclass pairwise discriminant loss; triplet loss; discriminative deep feature representation extraction; softmax; improved deep face identification; general deep convolutional neural network learning framework; identification protocols

Subjects: Computer vision and image processing techniques; Neural computing techniques; Image recognition; Knowledge engineering techniques

References

    1. 1)
      • 3. Wu, X., He, R., Sun, Z.: ‘A lightened CNN for deep face representation’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015.
    2. 2)
      • 6. Chen, D., Cao, X., Wang, L., et al: ‘Bayesian face revisited: a joint formulation’. European Conf. Computer Vision (ECCV), Firenze, Italy, October 2012, pp. 566579, doi: 10.1007/978-3-642-33712-3_41.
    3. 3)
      • 2. Schroff, F., Kalenichenko, D., Philbin, J.: ‘Facenet: a unified embedding for face recognition and clustering’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015, pp. 815823, doi: 10.1109/CVPR.2015.7298682.
    4. 4)
    5. 5)
      • 1. Parkhi, O.M., Vedaldi, A., Zisserman, A.: ‘Deep face recognition’. British Machine Vision Conf. (BMVC), Swansea, UK, September 2015, 1, (3), pp. 112, doi: 10.1109/78.790650.
    6. 6)
    7. 7)
      • 4. Taigman, Y., Yang, M., Ranzato, M., et al: ‘Web-scale training for face identification’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015, pp. 27462754, doi: 10.1109/CVPR.2015.7298891.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.2108
Loading

Related content

content/journals/10.1049/el.2017.2108
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading