Multilingual scene character recognition with co-occurrence of histogram of oriented gradients
详细信息 查看全文
- 作者：Shangxuan Tiana ; tianshangxuan@u.nus.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Ujjwal Bhattacharyac ; ujjwal@isical.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Shijian Lub ; slu@i2r.a-star.edu.sg" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Bolan Sub ; subl@i2r.a-star.edu.sg" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Qingqing WangdAuthor Vitae ; Xiaohua WeidAuthor Vitae ; Yue Lud ; ylu@cs.ecnu.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Chew Lim Tana ; tancl@comp.nus.edu.sg" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Multilingual Scene Text ; Histogram of Oriented Gradients ; Co-occurrence HOG ; Scene Character Recognition
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：March 2016
- 年：2016
- 卷：51
- 期：Complete
- 页码：125-134
- 全文大小：1549 K
文摘
- •
Introduced powerful features Co-HOG and ConvCo-HOG for scene character recognition.
- •
Designed a new offset based strategy for dimension reduction of above features.
- •
Developed two new scene character datasets for Chinese and Bengali scripts.
- •
Extensive simulations on 5 datasets of 3 scripts show the efficiency of the approach.