Research on Text Detection of Network Advertising Images Based on Deep Learning

DOI

10.2991/fmsmt-17.2017.43How to use a DOI?

Keywords

Text detection, Network advertising images, Deep learning

Abstract

The text detection of advertising images is of great significance in current economic life. The traditional method of text detection often omits words or wrongly detects the text. In this paper, the deep learning algorithm is introduced to detect the text in the online advertising images. Based on the algorithm of restricted Boltzmann machine, this paper improves the accuracy and speed of the traditional algorithm.

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  - Pokwai To
PY  - 2017/04
DA  - 2017/04
TI  - Research on Text Detection of Network Advertising Images Based on Deep Learning
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 207
EP  - 210
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.43
DO  - 10.2991/fmsmt-17.2017.43
ID  - To2017/04
ER  -