IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 9 - Issue 2, February 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Grassmann: Face Based Recognition Using Convolutional Neural Network In Deep Learning

[Full Text]

 

AUTHOR(S)

R.Elankeerthana K.Kokila

 

KEYWORDS

Face recognition, Traditional methodology, C-NN, Grassmann manifold learning approach.

 

ABSTRACT

Individual re-distinguishing proof is a key subject in the field of the computer vision innovations. The conventional (traditional) strategies for individual re-identification proof experience issues in taking care of the issues of individual brightening, impediment and frame of mind change under complex foundation. Then, the presentation of profound learning opens another method for individual re-recognizable proof research and turns into a problem area in this field. In any case, pictures got by CCTV cameras are generally of low quality. Second, an image objective is regularly lower for video progressions. If the subject is far from the camera, the certifiable face picture objectives can be as low as 64 by 64 pixels. Last, face picture assortments, for instance, light, appearance, stance, obstruction, and development, are dynamically genuine in video progressions. The philosophy can address the uneven movements between still pictures and chronicles overwhelmingly by creating various "ranges" to interface the still pictures and video traces. So in this endeavor, we can complete still to video planning approach to manage coordinate the photos with accounts using Grassmann manifold learning approach and Convolutional Neural system calculation to know darken matches. Utilizing Grassmann learning calculation to scrutinize the features vectors and organizing segment vectors reliant on significant learning draws near. Finally give voice alert at the time darken organizing continuously circumstances and besides give SMS alert and Email alert at the period of cloud face area.

 

REFERENCES

[1] Fangyi Liu Lei Zhang “View Confusion Feature Learning for Person Re-identification” arXiv:1910.03849v1 [cs.CV] 9 Oct 2019.
[2] Ergys Ristani, Carlo Tomasi., (2018). Features for Multi-Target Multi-Camera Tracking and Re-Identification. in ArXiv, CVPR.
[3] I. B. Barbosa, M. Cristani, B. Caputo, A. Rognhaugen, and T. Theoharis. Looking beyond appearances: Synthetic training data for deep CNNs in re-identification. arXiv preprinted Xiv: 1701.03153, 2017.
[4] L. Beyer, S. Breuers, V.Kurin, and B. Leibe. Towards a principled integration of multi-camera re-identification and tracking through optimal bayes filters. CVPRWS, 2017.
[5] Y. Chen, X. Zhu, and S. Gong. Person re-identification by deep learning multi-scale representations. 2017.
[6] Z. Cao, T. Simon, S.-E.Wei, and Y. Sheikh. Real time multi-person 2d pose estimation using part affinity fields. In CVPR, 2017.
[7] A. Dehghan, S. M. Assari, and M. Shah. Gmmcp tracker: Globally optimal generalized maximum multi clique problem for multiple object tracking. In CVPR, volume 1, page 2, 2015.
[8] D. Baltieri, R. Vezzani, and R. Cucchiara. Mapping appearance descriptors on 3d body models for people re-identification. International Journal of Computer Vision, 111(3):345–364, 2015.
[9] L. Cao, W. Chen, X. Chen, S. Zheng, and K. Huang. An equalized global graphical model-based approach for multi-camera object tracking.ArXiv:11502.03532 [Cs], Feb. 2015.
[10] V. Chari, S. Lacoste-Julien, I. Laptev, and J. Sivic. On pair wise costs for network flow multi-object tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5537–5545, 2015.