Logo Localization and Recognition Based on Spatial Pyramid Matching with Color Proportion

DOI

10.2991/icmt-13.2013.223How to use a DOI?

Keywords

Logo Localization, Logo Recognition, Efficient Subwindow Search, Color Proportion

Abstract

In this paper, we propose a novel logo localization and recognition model in which we use the spatial pyramid matching with color proportion to train a score function and the Efficient Subwindow Search (ESS) to localize region and recognize specific logo. Our model has two advantages compared with other related algorithms: (1) this model has a O (n ^2) time complexity in localizing logo regions which is much faster than the traditional sliding window approaches that has a time complexity of O (n ^4) which make it cannot apply to real world applications because of the high computational cost; (2) by means of our well-designed spatial pyramid matching embedded by color proportion, we can achieve a higher recognition rate even with the linear kernel SVM. We test our model in a logo dataset called FlickrLogos-32 which contains 32 different logo classes by downloading them from Flickr. Experiments show that our model both have fast enough speed and high correct rate.

Copyright

© 2013, 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  - Feng Wenya
AU  - Chen Zhiqian
AU  - Hou Yonggan
AU  - Liu Long
AU  - Guo Yilin
PY  - 2013/11
DA  - 2013/11
TI  - Logo Localization and Recognition Based on Spatial Pyramid Matching with Color Proportion
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 1839
EP  - 1846
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.223
DO  - 10.2991/icmt-13.2013.223
ID  - Wenya2013/11
ER  -