Enhancing energy minimization framework for scene text recognition with top-down cues
详细信息 查看全文
- 作者：Anand Mishra ; a ; anand.mishra@research.iiit.ac.in" class="auth_mail" title="E-mail the corresponding author ; anandmishra.jsp@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Karteek Alaharib ; C.V. Jawahara
- 关键词：Scene text understanding ; Text recognition ; Lexicon priors ; Character recognition ; Random field models
- 刊名：Computer Vision and Image Understanding
- 出版年：2016
- 出版时间：April 2016
- 年：2016
- 卷：145
- 期：Complete
- 页码：30-42
- 全文大小：1654 K
文摘
- class="listitem" id="list_celist0001">
- class="label">•
An energy minimization based approach for scene text recognition with seamless integration of multiple cues.
- class="label">•
Applied also to the challenging open vocabulary setting, where a word-specific lexicon is unavailable.
- class="label">•
Comprehensive experimental evaluation on several state-of-the-art benchmarks.