Container Code Detection by Deep Convolutional Network

DOI

10.2991/gcmce-17.2017.16How to use a DOI?

Keywords

Container code recognition, Deep convolutional network, Holistic-nested edge detection.

Abstract

Automatic container code recognition plays an important role in customs logistics and tra-nsport management. Due to difficulties such as character color and font size variation, illumination conditions, image degradation, and exist of many other characters, automatic detect and recognition of container code is still a difficult task. This paper proposes a container code detection algorithm based on deep convolutional neural network named holistically-nested edge detection (HED). In the training phase, a bounding box was drawn around container code as virtual edges, and they were feed to the network together with original image to train the HED model. In the test phase, probability map of bounding box was predict by trained model and finally bounding box is obtained by thresholding and connected region analysis. Experimental results on 9953 container images show that the performance of IOU and recall precision on test set can reach 0.646 and 0.934 respectively with the proposed algorithms.

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  - Zhiming Wang
AU  - Shu Ma
PY  - 2017/06
DA  - 2017/06
TI  - Container Code Detection by Deep Convolutional Network
BT  - Proceedings of the 2017 Global Conference on Mechanics and Civil Engineering (GCMCE 2017)
PB  - Atlantis Press
SP  - 82
EP  - 87
SN  - 2352-5401
UR  - https://doi.org/10.2991/gcmce-17.2017.16
DO  - 10.2991/gcmce-17.2017.16
ID  - Wang2017/06
ER  -