End-to-end scene text recognition using tree-structured models

• We build a part-based tree-structured model (TSM) for each category of character.
• The TSM utilizes character-specific global structure information.
• The TSMs connect detection and recognition together in a certain way.
• We propose the normalized pictorial structure framework to recognize words.
• The end-to-end system outperforms state-of-the-art methods considerably.

Detecting and recognizing text in natural images are quite challenging and have received much attention from the computer vision community in recent years. In this paper, we propose a robust end-to-end scene text recognition method, which utilizes tree-structured character models and normalized pictorial structured word models. For each category of characters, we build a part-based tree-structured model (TSM) so as to make use of the character-specific structure information as well as the local appearance information. The TSM could detect each part of the character and recognize the unique structure as well, seamlessly combining character detection and recognition together. As the TSMs could accurately detect characters from complex background, for text localization, we apply TSMs for all the characters on the coarse text detection regions to eliminate the false positives and search the possible missing characters as well. While for word recognition, we propose a normalized pictorial structure (PS) framework to deal with the bias caused by words of different lengths. Experimental results on a range of challenging public datasets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method outperforms state-of-the-art methods both for text localization and word recognition.