Face Identification through Learned Image High Feature Video Frame Works

Boya Akhila¹ , Burgubai Jyothi²

Section:Research Paper, Product Type: Isroset-Journal
Vol.6 , Issue.4 , pp.24-29, Aug-2018

CrossRef-DOI:   https://doi.org/10.26438/ijsrcse/v6i4.2429

Online published on Aug 31, 2018

Copyright © Boya Akhila, Burgubai Jyothi . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

547 Views    575 Downloads    189 Downloads

Abstract :
The affluence and possibility of video taking devices, such as mobiles and security cameras have inspired the search for video on face recognition which is very relevant in police applications. Whereas current paths have reported high accuracy errors, performance at lower prices for wrong acceptance requires important advancement. The choice of frames is followed by drawing features based on the representation of learning ,where three hand-outs are represented 1) Deep learning architecture, which is a mixture of low stacking automatic encoder (SDAE) and deep machine Boltzmann (DBM) 2) formulation for joint illustration in an automatic encoder 3) Improve the DBM loss function, including low range modification. At last a multilayer neural network is used as a classifier to get the verification decision. The results are shown in two public databases on hand, YouTube Faces,Point and Shoot Challenge. The new study suggests that 1) frame selection based on the quality of the proposed features gets extraordinary and steady performance compared to the front frame, casual frames or plot selection using perceptual image quality dimensions without reference and 2) SDAE features of Common learning and low DBM and low regularization range helps get better facial confirmation.

Key-Words / Index Term :
Deep Learning, Auto Encoder, Deep Boltzmann, Machine, Face Perception, Frame Selection

References :
[1] Facial recognition technology safeguards Beijing Olympics, accessed on Mar. 10, 2017 [Online]. Available: http://english.cas.cn/ resources/archive/china_archive/cn2008/200909/t20090923_42959.shtml
[2] J. Beveridge et al., “The challenge of face recognition from digital point-and-shoot cameras,” in Proc. IEEE Conf. Biometrics Theory, Appl. Syst., Oct. 2013, pp. 1–8.

[3] L. Wolf, T. Hassner, and I. Maoz, “Face recognition in unconstrained videos with matched background similarity,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2011, pp. 529–534.

[4] L. Wolf and N. Levy, “The SVM-minus similarity score for video face recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2013, pp. 3523–3530.

[5] H. Li, G. Hua, Z. Lin, J. Brandt, and J. Yang, “Probabilistic elastic matching for pose variant face verification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2013, pp. 3499–3506.

[6] Z. Cui, W. Li, D. Xu, S. Shan, and X. Chen, “Fusing robust face region descriptors via multiple metric learning for face recognition in the wild,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2013,

pp. 3554–3561.

[7] H. Méndez-Vázquez, Y. Martínez-Díaz, and Z. Chai, “Volume struc-tured ordinal features with background similarity measure for video face recognition,” in Proc. Int. Conf. Biometrics (ICB), Jun. 2013,

pp. 1–6.

[8] H. S. Bhatt, R. Singh, and M. Vatsa, “On recognizing faces in videos using clustering-based re-ranking and fusion,” IEEE Trans. Inf. Forensics Security, vol. 9, no. 7, pp. 1056–1068, Jul. 2014.

[9] J. Y. Junlin Hu, J. Lu, and Y.-P. Tan, “Large margin multi-metric learning for face and kinship verification in the wild,” in Proc. Asian Conf. Comput. Vis., 2014, pp. 252–267.

[10] J. Hu, J. Lu, and Y. Tan, “Discriminative deep metric learning for face verification in the wild,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2014, pp. 1875–1882.

[11] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, “DeepFace: Closing the gap to human-level performance in face verification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2014, pp. 1701–1708.

[12] W. Wang, R. Wang, Z. Huang, S. Shan, and X. Chen, “Discriminant analysis on riemannian manifold of Gaussian distributions for face recognition with image sets,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 2048–2057.

[13] N. M. Khan, X. Nan, A. Quddus, E. Rosales, and L. Guan, “On video based face recognition through adaptive sparse dictionary,” in Proc. IEEE Int. Conf. Workshops Autom. Face Gesture Recognit., May 2015,

pp. 1–6.

[14] H. Li, G. Hua, X. Shen, Z. Lin, and J. Brandt, “Eigen-PEP for video face recognition,” in Proc. Asian Conf. Comput. Vis., 2014, pp. 17–33.

[15] H. Li and G. Hua, “Hierarchical-PEP model for real-world face recog-nition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015,

pp. 4055–4064.