arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.06535cs.CV
收藏

不止一次查找:一个精确的任意字符串文本检测器

Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes

Baidu Inc(百度公司);Xiamen University(厦门大学)

Chengquan Zhang, Borong Liang, Zuming Huang, Mengyi En, Junyu Han, Errui Ding, Xinghao Ding

摘要:

在过去的几年里,以前的场景文本检测方法已经取得了很大的进展。然而,由于受CNN的接收域和描述文本的矩形限界框或四边形等简单表示的限制,以前的方法在处理更具有挑战性的文本实例时可能会有所不足,例如超长文本和任意形状的文本。为了解决这两个问题,我们提出了一种新的文本检测器,即LOMO,它逐步定位文本多次(或换句话说,LOOK不止一次)。LOMO由一个直接回归器(DR),一个迭代细化模块(RESIDENCE)和一个形状表达模块(SEM)。首先,由DR分支生成四边形形式的文本建议。接下来,通过基于初步建议的提取的特征块的迭代细化,ESTA逐步感知整个长文本。最后,SEM被引入到重建更精确的不规则文本的表示,通过考虑文本实例的几何属性,包括文本区域,文本中心线和边界偏移。包括ICDAR 2017-RCTW、SCUT-CTW 1500、Total-Text、ICDAR 2015和ICDAR 17-MLT在内的多个公共基准测试的最新结果证实了LOMO的强大和有效性。

英文摘要:

Previous scene text detection methods have progressed substantially over the past years. However, limited by the receptive field of CNNs and the simple representations like rectangle bounding box or quadrangle adopted to describe text, previous methods may fall short when dealing with more challenging text instances, such as extremely long text and arbitrarily shaped text. To address these two problems, we present a novel text detector namely LOMO, which localizes the text progressively for multiple times (or in other word, LOok More than Once). LOMO consists of a direct regressor (DR), an iterative refinement module (IRM) and a shape expression module (SEM). At first, text proposals in the form of quadrangle are generated by DR branch. Next, IRM progressively perceives the entire long text by iterative refinement based on the extracted feature blocks of preliminary proposals. Finally, a SEM is introduced to reconstruct more precise representation of irregular text by considering the geometry properties of text instance, including text region, text center line and border offsets. The state-of-the-art results on several public benchmarks including ICDAR2017-RCTW, SCUT-CTW1500, Total-Text, ICDAR2015 and ICDAR17-MLT confirm the striking robustness and effectiveness of LOMO.

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。

↑