Back to Search Start Over

Focusing Attention: Towards Accurate Text Recognition in Natural Images

Authors :
Cheng, Zhanzhan
Bai, Fan
Xu, Yunlu
Zheng, Gang
Pu, Shiliang
Zhou, Shuigeng
Cheng, Zhanzhan
Bai, Fan
Xu, Yunlu
Zheng, Gang
Pu, Shiliang
Zhou, Shuigeng
Publication Year :
2017

Abstract

Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. However, we observe that existing attention-based methods perform poorly on complicated and/or low-quality images. One major reason is that existing methods cannot get accurate alignments between feature areas and targets for such images. We call this phenomenon "attention drift". To tackle this problem, in this paper we propose the FAN (the abbreviation of Focusing Attention Network) method that employs a focusing attention mechanism to automatically draw back the drifted attention. FAN consists of two major components: an attention network (AN) that is responsible for recognizing character targets as in the existing methods, and a focusing network (FN) that is responsible for adjusting attention by evaluating whether AN pays attention properly on the target areas in the images. Furthermore, different from the existing methods, we adopt a ResNet-based network to enrich deep representations of scene text images. Extensive experiments on various benchmarks, including the IIIT5k, SVT and ICDAR datasets, show that the FAN method substantially outperforms the existing methods.<br />Comment: Revise the description of IC15 datasets (1811 samples)

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1106274398
Document Type :
Electronic Resource
Full Text :
https://doi.org/10.1109.ICCV.2017.543