Fast Deformation Part Model with CNN for Face Detection

DOI

10.2991/ncce-18.2018.65How to use a DOI?

Keywords

DPM; filter pyramid; scale invariance; face detection

Abstract

This paper proposes a fast deformation part model (DPM) with neural network (FDPDPM) for face detection. It can make fully use of the advantage of high level feature and classifier with spatial location information. In fact, this paper uses a truncated the variant of VVGNET and a pyramid of multi-scale filter method to maintain the scale invariance. As a result, it not only improves the detection efficiency, but also makes a contribution to better detection effect on the face with small size and partial occlusion

Copyright

© 2018, 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  - Canzhang Guo
AU  - Yinwei Zhan
PY  - 2018/05
DA  - 2018/05
TI  - Fast Deformation Part Model with CNN for Face Detection
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 408
EP  - 413
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.65
DO  - 10.2991/ncce-18.2018.65
ID  - Guo2018/05
ER  -