Advertisement

Face Recognition Algorithm for Low-Resolution Images

  • Monika Rani Golla
  • Poonam Sharma
  • Jitendra MadarkarEmail author
Conference paper
  • 13 Downloads
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 100)

Abstract

Recently, in the field of face recognition, deep learning has achieved great success. FaceNet, one of the Google’s deep learning frameworks, obtained nearly 100% accuracy in recognizing high-resolution faces. But, its performance on low-resolution images is unsatisfactory. Here, to justify the above statement, the performance of FaceNet has been evaluated on four well-known facial databases. For improving the performance, the face recognition algorithm for low-resolution images has been designed. Specifically, the algorithm performs image enhancement using a customized error back propagation network, and then the nearest patterns (NP) have been extracted and fed as embeddings to FaceNet. NP is a modified version of dual-cross patterns face descriptor that encodes the texture information of each image pixel in eight directions as unique features. The experimentation done on various databases such as LFW, ORL, EYB, and AR. The results of proposed approaches with NP have shown better performance than the other face descriptors like DCP, LBP, and LTP. Moreover, better results have been obtained on shrinking the Inception-Resnet-v1 network, which resulted in the fast convergence of the FaceNet.

Keywords

Face recognition Low resolution FaceNet Local binary pattern Face descriptor 

References

  1. 1.
    Sharma P, Yadav RN, Arya KV (2014) Pose invariant face recognition using curvelet neural network. IET Biom 3(3):128–138CrossRefGoogle Scholar
  2. 2.
    Turk Matthew, Pentland Alex (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86CrossRefGoogle Scholar
  3. 3.
    Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041CrossRefGoogle Scholar
  4. 4.
    Bartlett MS, Movellan JR, Sejnowski TJ (2002) Face recognition by independent component analysis. IEEE Trans Neural Netw 13(6):1450–1464CrossRefGoogle Scholar
  5. 5.
    Sharma P, Arya KV, Yadav RN (2013) Efficient face recognition using generalized mean wavelet neural network. Signal Process 93(6):1557–1565. SCI Journal (impact factor 2.238)Google Scholar
  6. 6.
    Phillips PJ (1999) Support vector machines applied to face recognition. In: David AC (ed) Proceedings of the 1998 conference on advances in neural information processing systems II, 1999. MIT Press, Cambridge, MA, USA, pp 803–809Google Scholar
  7. 7.
    Sharma P, Arya KV, Yadav RN (2011) Extraction of facial features using higher order moments in curvelet transform and recognition using generalized mean neural networks. In: International conference on soft computing for problem solving at IIT Roorkee, vol 131, pp 717–728, 20–22 Dec 2011Google Scholar
  8. 8.
    Sharma P, Yadav RN, Arya KV (2016) Face recognition from video using generalized mean deep learning neural network. In: 2016 4th international symposium on computational and business intelligence (ISCBI). Olten, pp 195–199Google Scholar
  9. 9.
    Arya KV, Upadhyay G, Upadhyay S, Tiwari S, Sharma P (2016) Facial recognition using histogram of Gabor phase patterns and self organizing maps. In: 2016 11th international conference on industrial and information systems (ICIIS). Roorkee, pp 883–889Google Scholar
  10. 10.
    Ghazi MM, Ekenel HK (2016) A comprehensive analysis of deep learning based representation for face recognition. In: 2016 IEEE conference on computer vision and pattern recognition workshops (CVPRW). Las Vegas, NV, pp 102–109Google Scholar
  11. 11.
    Kurmi US, Agrawal D, Baghel RK (2014) Study of different face recognition algorithms and challenges. Int J Eng Res 3:112–115.  https://doi.org/10.17950/ijer/v3s2/216CrossRefGoogle Scholar
  12. 12.
    Li Z, Hou Y, Liu H, Li X (2014) Very low resolution face reconstruction based on multi-output regression. In: IEEE workshop on electronics, computer and applications. Ottawa, ON, pp 74–77Google Scholar
  13. 13.
    Shi J, Qi C (2015) From local geometry to global structure: learning latent subspace for low-resolution face image recognition. IEEE Signal Process Lett 22(5):554–558CrossRefGoogle Scholar
  14. 14.
    Kaur R, Himanshi E (2015) Face recognition using principal component analysis. In: IEEE international advance computing conference (IACC). Bangalore, pp 585–589Google Scholar
  15. 15.
    Xu Y, Jin Z (2008) Down-sampling face images and low-resolution face recognition. In: 3rd international conference on innovative computing information and control. Dalian, Liaoning, pp 392–392Google Scholar
  16. 16.
    Raghavendra R, Raja KB, Yang B, Busch C (2013) Comparative evaluation of super-resolution techniques for multi-face recognition using light-field camera. In: 2013 18th international conference on digital signal processing (DSP). Fira, pp 1–6Google Scholar
  17. 17.
    Jia K, Gong SG (2005) Multi-modal tensor face for simultaneous super-resolution and recognition. In: Proceedings of IEEE 10th international conference on computer vision (ICCV), vol 2. Beijing, China, pp 1683–1690Google Scholar
  18. 18.
    Choi JY, Ro YM, Plataniotis KN (2009) Color face recognition for degraded face images. IEEE Trans Syst Man Cybern, Part B, Cybern 39(5):1217–1230Google Scholar
  19. 19.
    Biswas S, Bowyer KW, Flynn PJ (2012) Multidimensional scaling for matching low-resolution face images. IEEE Trans Pattern Anal Mach Intell 34(10):2019–2030CrossRefGoogle Scholar
  20. 20.
    Ren CX, Dai DQ, Yan H (2012) Coupled kernel embedding for low-resolution face recognition. IEEE Trans Image Process 21(8):3770–3783MathSciNetCrossRefGoogle Scholar
  21. 21.
    Tran CK, Lee TF, Tuan CC, Lu CH, Chao PJ (2013) Improving face recognition performance using similarity feature-based selection and classification algorithm. In: 2013 Second international conference on robot, vision and signal processing. Kitakyushu, pp 56–60Google Scholar
  22. 22.
    Ding C, Choi J, Tao D, Davis LS (2016) Multi-directional multi-level dual-cross patterns for robust face recognition. IEEE Trans Pattern Anal Mach Intell 38(3):518–531CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Monika Rani Golla
    • 1
  • Poonam Sharma
    • 1
  • Jitendra Madarkar
    • 1
    Email author
  1. 1.Department of Computer Science and EngineeringVisvesvaraya National Institute of TechnologyNagpurIndia

Personalised recommendations