arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.10977cs.CV
收藏

SEED:语义增强的场景文本识别编解码框架

SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)

Zhi Qiao, Yu Zhou, Dongbao Yang, Yucan Zhou, Weiping Wang

摘要:

场景文本识别是计算机视觉的一个研究热点。近年来,许多基于编码器-解码器框架的识别方法已经被提出,并且它们可以处理具有透视变形和曲线形状的场景文本。尽管如此,它们仍然面临着许多挑战,如图像模糊,光照不均匀和不完整的字符。我们认为,大多数编码器-解码器的方法是基于本地的视觉特征,没有明确的全局语义信息。在这项工作中,我们提出了一个语义增强的编码器-解码器框架,以鲁棒地识别低质量的场景文本。语义信息在编码器模块中用于监督,在解码器模块中用于初始化。特别是,国家的最先进的ASTER方法集成到建议的框架作为范例。大量实验表明,该框架对低质量文本图像具有更强的鲁棒性,并在多个基准数据集上取得了最佳效果。

英文摘要:

Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape. Nevertheless, they still face lots of challenges like image blur, uneven illumination, and incomplete characters. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we propose a semantics enhanced encoder-decoder framework to robustly recognize low-quality scene texts. The semantic information is used both in the encoder module for supervision and in the decoder module for initializing. In particular, the state-of-the art ASTER method is integrated into the proposed framework as an exemplar. Extensive experiments demonstrate that the proposed framework is more robust for low-quality text images, and achieves state-of-the-art results on several benchmark datasets.

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。

↑