arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.02054cs.CV
收藏

聚焦注意力:实现自然图像中的精确文本识别

Focusing Attention: Towards Accurate Text Recognition in Natural Images

Hikvision Research Institute(海康威视研究院);Shanghai Jiaotong University(上海交通大学)

Zhanzhan Cheng, Fan Bai, Yunlu Xu, Gang Zheng, Shiliang Pu, Shuigeng Zhou

摘要:

场景文本识别因其广泛的应用而成为计算机视觉的研究热点。最先进的是基于注意力的编码器-解码器框架,它以纯粹的数据驱动方式学习输入图像和输出序列之间的映射。然而,我们观察到现有的基于注意力的方法在复杂和/或低质量的图像上表现不佳。一个主要原因是,现有的方法不能得到准确的特征区域和目标之间的对齐,这样的图像。我们称这种现象为“注意力漂移”。为了解决这个问题,在本文中,我们提出了FAN(集中注意力网络的缩写)的方法,采用聚焦注意力机制自动拉回漂移的注意力。FAN由两个主要组成部分组成:一个注意力网络(AN),负责识别字符目标,如现有的方法,和一个聚焦网络(FN),负责调整注意力,通过评估AN是否适当地关注图像中的目标区域。此外,与现有方法不同,我们采用基于ResNet的网络来丰富场景文本图像的深度表示。在IIIT 5 k、SVT和ICDAR数据集上进行的大量实验表明,FAN方法的性能明显优于现有方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑