Proceedings of the 2015 International conference on Applied Science and Engineering Innovation

Deep Learning based Model for Prohibited Goods Detection

Authors
Zhao Liu, Ying Ruan, Chun Chen
Corresponding Author
Zhao Liu
Available Online May 2015.
DOI
10.2991/asei-15.2015.23How to use a DOI?
Keywords
Prohibited goods; Deep Convolutional Neural Networks; Deep Belief Networks
Abstract

With the rapid development of Internet technology, massive images are used on e-commerce sites to show product details. Among those images there are some of contraband, which seriously harm the social harmony, thus it is important to automatically identify them. In this paper, we propose an effective method aims at solving this problem, in contrast with traditional methods, we do not use human designed visual features and classification models, but combine deep features and deep learning model. Experiment results show that our method outperform previous human designed features and visual models tremendously.

Copyright
© 2015, 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)

Volume Title
Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
Series
Advances in Engineering Research
Publication Date
May 2015
ISBN
978-94-62520-94-3
ISSN
2352-5401
DOI
10.2991/asei-15.2015.23How to use a DOI?
Copyright
© 2015, 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/).

Cite this article

TY  - CONF
AU  - Zhao Liu
AU  - Ying Ruan
AU  - Chun Chen
PY  - 2015/05
DA  - 2015/05
TI  - Deep Learning based Model for Prohibited Goods Detection
BT  - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
PB  - Atlantis Press
SP  - 103
EP  - 106
SN  - 2352-5401
UR  - https://doi.org/10.2991/asei-15.2015.23
DO  - 10.2991/asei-15.2015.23
ID  - Liu2015/05
ER  -