Face Detection Algorithm Based on Convolutional Pooling Deep Belief Network

DOI

10.2991/eame-17.2017.64How to use a DOI?

Keywords

face detection; deep learning; CPDBN; partial occlusion

Abstract

When using a single deep model to solve the problem of face detection, it is easy to have the problem of high false detection rate and low learning efficiency, the mixed model algorithm based on deep learning was proposed to solve these problems of face detection, which is called the CPDBN (Convolutional pooling deep belief network). Experimental results show that the algorithm improves the accuracy of face detection in the face of partial occlusion, and increases the robustness of multi-pose.

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  - Dandan Wang
AU  - Ming Li
AU  - Xiaoxu Li
PY  - 2017/04
DA  - 2017/04
TI  - Face Detection Algorithm Based on Convolutional Pooling Deep Belief Network
BT  - Proceedings of the 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017)
PB  - Atlantis Press
SP  - 273
EP  - 276
SN  - 2352-5401
UR  - https://doi.org/10.2991/eame-17.2017.64
DO  - 10.2991/eame-17.2017.64
ID  - Wang2017/04
ER  -