Abstract

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. Different from conventional multi-scale sliding window character detection strategy, which does not make use of the character-specifific structure information, we use part-based tree-structure to model each type of character so as to detect 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 incorporate the detection scores, spatial constraints and linguistic knowledge into one framework. The fifinal word recognition result is obtained by minimizing the cost function defifined on the random fifield. Experimental results on a range of challenging public datasets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method outperforms stateof-the-art methods signifificantly both for character detection and word recognition.