Scene Text Recognition using Part-based Tree-structured Character Detection," CVPR

Scene text recognition has inspired great interests from the computer vision community in recent years. In this paper, we propose a novel scene text recognition method using part-based tree-structured character detection. Dif-ferent from conventional multi-scale sliding window char-acter detection strategy, which does not make use of the character-specific structure information, we use part-based tree-structure to model each type of character so as to de-tect and recognize the characters at the same time. While for word recognition, we build a Conditional Random Field model on the potential character locations to incorpo-rate the detection scores, spatial constraints and linguistic knowledge into one framework. The final word recognition result is obtained by minimizing the cost function defined on the random field. Experimental results on a range of chal-lenging public datasets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method outperforms state-of-the-art methods significantly both for character detection and word recognition. 1