Pose Invariant Face Recognition for New Born: Machine Learning Approach

  • Rishav SinghEmail author
  • Hari Om
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 410)


Pose is a natural and important covariate in case of newborn and face recognition across pose can troubleshoot the approaches dealing with uncooperative subjects like newborn, in which the full power of face recognition being a passive biometric technique requires to be implemented and utilized. To handle the large pose variation in newborn, we propose a pose-adaptive similarity method that uses pose-specific classifiers to deal with different combinatorial poses. A texture based face recognition method, Speed Up Robust Feature (SURF) transform, is used to compare the descriptor of testing (probe) face with given training (gallery) face descriptor. Probes executed on the face template data of newborn described here, offer comparative benefits towards affinity for pose variations and the proposed algorithm verdicts the rank 1 accuracy of 92.1 %, which demonstrates the strength of self learning even with single training face image of newborn.


SURF Face recognition Machine learning Classification Regression 



The authors would like to thank Dr. Shrikant Tiwari (Department of Computer Science and Engineering, IIT (BHU) for providing database of newborn.


  1. 1.
    Jia, W., Cai, H., Gui, J., et al.: Newborn footprint recognition using orientation feature. J. Neural Comput. Appl. 21(8), 1855–1863 (2012)CrossRefGoogle Scholar
  2. 2.
    Gray, J.E., Suresh, G., Ursprung, R., Edwards, W.H., Nickerson, J., Shinno, P.H.: Patient misidentification in the neonatal intensive careunit: quantification of risk. Pediatrics 117, e46–e47 (2006)CrossRefGoogle Scholar
  3. 3.
  4. 4.
    Stapleton, M.E.: Best foot forward: newborn footprints for personalidentification. FBI Law Enforcement Bull. 63(11), 1999Google Scholar
  5. 5.
    Thompson, J.E., Clark, D.A., Salisbury, B., Cahill, J.: Footprinting the: not cost-effective. J. Pediatr. 99, 797–798 (1981)CrossRefGoogle Scholar
  6. 6.
    Galton, F.: Finger prints of young children (British Association for the Advancement of Science, 1899)Google Scholar
  7. 7.
    Shepard, K.S., Erickson, T., Fromm, H.: Limitations of footprinting as a means of newborn identification. Pediatrics 37(1), 107–108 (1966)Google Scholar
  8. 8.
    Pela, N.T.R., Mamede, M.V., Tavares, M.S.G.: Analise crtica de impressoes plantares de recem-nascidos. Revista Brasileira de Enfermagem 29, 100–105 (1975)CrossRefGoogle Scholar
  9. 9.
    Weingaertner, D., Bellon, O.R.P., Cat, M.N.L., Silva, L.: Newborn’s biometric identification: can it be done? Int. Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2008Google Scholar
  10. 10.
    Fields, C., Hugh, C.F., Warren, C.P., Zimberoff, M.: The ear of the newborn as an identification constant. J. Obstet. Gynecol. 16, 98–101 (1960)Google Scholar
  11. 11.
    Lemes, R.P., Bellon, O.R.P., Silva, L., Jain, A.K.: Biometric recognition of newborns: identification using palmprints, pp. 11–13. Int. Joint Conf. Biometrics, Washington, DC, USA (2011)Google Scholar
  12. 12.
    Tiwari, S., Singh, S.K.: Face recognition for newborns. IET Biometrics. 1(4), 200–208 (2012)CrossRefGoogle Scholar
  13. 13.
    Tiwari, S., Singh, S.K.: Newborn verification using headprint. J. Inform. Technol. Res. (JITR), 5(2), 15–30, April–June 2012, ISSN: 1938-7857, doi: 10.4018/jitr.2012040102. (IGI Global)Google Scholar
  14. 14.
    Tiwari, S., Singh, A., Singh, S.K.: Fusion of ear and soft-biometrics for recognition of newborn. Sign. Image Process.: Int. J. 3(3), 103–116, ISSN: 0976-710X (2012)Google Scholar
  15. 15.
    Tiwari, S., Singh, Aruni, Singh, S.K.: Intelligent method for face recognition of infant. Int. J. Comput. Appl. 52(4), 36–50 (2012)Google Scholar
  16. 16.
    Tiwari, Shrikant, Singh, Aruni, Singh, Sanjay Kumar: Integrating Faces and Soft-biometrics for Newborn Recognition. Int. J. Adv. Comput. Eng. Archit. 2(2), 201–209 (2012)MathSciNetGoogle Scholar
  17. 17.
    Tiwari, S., Singh, A., Singh, S.K.: Can Face and Soft-biometric Traits Assist in Recognition of Newborn? In: Proceedings of IEEE, International Conference on Recent Advanced in Information Technology, pp. 74–79, March 2012Google Scholar
  18. 18.
    Tiwari, S., Singh, A., Singh, S.K.: Can Ear and Soft-biometric Traits Assist in Recognition of Newborn? In: Proceedings of International Conference on Computer Science, Engineering and Applications, doi: 10.1007/978-3-642-30157-5, ISBN: 978-3-642-30157-5, pp. 179–192. Springer, Berlin (May 2012)Google Scholar
  19. 19.
    Tiwari, S., Singh, S.K., Multimodal Biometric Recognition for Newborn. In: Srivastava, R., Singh, S.K., Shukla, K.K. (eds.) Research Developments in Biometrics and Video Processing Techniques (IGI Global Publishing). Chapter 2. ISSN: 1948-9730, ISBN: 978-1-4666-4870-8Google Scholar
  20. 20.
    Tiwari, S., Singh, A., Singh, S.K.: Multimodal database of newborns for biometric recognition. Int. J. Bio-Sci. Bio-Technol. 5(2), 89–99 (2013)Google Scholar
  21. 21.
    Tiwari, S., Singh, A., Singh S.K.: Newborn’s ear recognition: can it be done?. In: International Conference on Image Information Processing (ICIIP), JUIT India, 3–5 November 2011Google Scholar
  22. 22.
    Keogh, E., Wei, L.: Semi-supervised time series classification. In: SIGKKD (2006)Google Scholar
  23. 23.
    Chapelle, O., Scholkopf, B., Zien, A.: Semi-Supervised Learning. The MIT Press, Cambridge (2006)CrossRefGoogle Scholar
  24. 24.
    Dillon, J.V., Balasubramanian, K., Lebanon, G.: Asymptotic analysis of generative semi-supervised learning. In: Appearing in Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel (2010)Google Scholar
  25. 25.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: speeded up robust features. Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  26. 26.
    Giraldo, J., Vivas, N.M., Vila, E., Badia, A.: Assessing the (a) symmetry of concentration-effect curves: empirical versus mechanistic models. Pharmacol. Ther. 95(1), 21–45 (2002)CrossRefGoogle Scholar
  27. 27.
    Richards, F.J.: A flexible growth function for empirical use. J. Exp. Bot. 10, 290–300 (1959)CrossRefGoogle Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  1. 1.Department of Computer Science & EngineeringIndian School of MinesDhanbadIndia

Personalised recommendations