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

作者：

Highlights：

• 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.

摘要

Highlights•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.

论文关键词：End-to-end,Scene text recognition,Part-based tree-structured models (TSMs),Normalized pictorial structure

论文评审过程：Received 20 June 2013, Revised 27 January 2014, Accepted 23 March 2014, Available online 1 April 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.03.023