On-premise signs detection and recognition using fully convolutional networks

Yong Xiang Wang, Chih Hsin Hsueh, Hung Yi Loo, Min Chun Hu

研究成果: Conference contribution

摘要

Convolutional neural network has been recently studied and used in many object recognition tasks. In this work, we employ fully convolutional networks (FCNs) to recognize On-Premise Signs (OPS) in real scene. This technology is capable of being utilized in many camera-enabled devices like smart phones to develop practical commercial applications. The fully convolutional network technique is used to train a model to infer whether a street view image contains a specific OPS and where the OPS locates in the input image. Furthermore, to improve the detection performance, data augmentation approaches are applied in our work, and the experiment results show our model outperforms the previous tasks.

原文English
主出版物標題2016 IEEE International Conference on Multimedia and Expo, ICME 2016
發行者IEEE Computer Society
ISBN(電子)9781467372589
DOIs
出版狀態Published - 2016 八月 25
事件2016 IEEE International Conference on Multimedia and Expo, ICME 2016 - Seattle, United States
持續時間: 2016 七月 112016 七月 15

出版系列

名字Proceedings - IEEE International Conference on Multimedia and Expo
2016-August
ISSN(列印)1945-7871
ISSN(電子)1945-788X

Other

Other2016 IEEE International Conference on Multimedia and Expo, ICME 2016
國家United States
城市Seattle
期間16-07-1116-07-15

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

指紋 深入研究「On-premise signs detection and recognition using fully convolutional networks」主題。共同形成了獨特的指紋。

引用此