Distributed Face Recognition Using Hadoop

DOI

10.2991/iccasp-16.2017.63How to use a DOI?

Keywords

MapReduce, Face Recognition, Distributed video analysis, Parallel computing.

Abstract

This paper introduces a scalable and flexible solution for face recognition using distributed Hadoop cluster. With the increase of use of CCTV for security purposes there is a need of efficient solution to utilize the vast data generated by them .In case of an investigation it is ideally required that the evidences are evaluated as fast as possible. Usually a week's recording of a CCTV footage is approximately 100 GB. Hence in this proposed solution we use avconv, OpenCV and Hadoop MapReduce for fast distributed video processing. We have experimented and analyzed the performance of facial recognition on different models and distributed configuration. We found Hadoop as an effective framework for video processing to recognize face.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - A. Thorat
AU  - V. Malhotra
AU  - S. Narvekar
AU  - A. Joshi
PY  - 2016/12
DA  - 2016/12
TI  - Distributed Face Recognition Using Hadoop
BT  - Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)
PB  - Atlantis Press
SP  - 419
EP  - 424
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccasp-16.2017.63
DO  - 10.2991/iccasp-16.2017.63
ID  - Thorat2016/12
ER  -