arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.04348cs.CV
收藏

用于鲁棒文本抽取的字符建议网络

Character Proposal Network for Robust Text Extraction

South China University of Technology(华南理工大学);Sun Yat-Sen University(中山大学)

Shuye Zhang, Mude Lin, Tianshui Chen, Lianwen Jin, Liang Lin

摘要:

最大稳定极值区域(MSER),这是一种流行的方法来产生字符建议/候选人,在场景文本检测表现出优越的性能。然而,像素级操作限制了其处理一些具有挑战性的情况(例如,多个连接的字符、一个字符的分离部分和非均匀照明)。为了更好地解决这些问题,我们利用全卷积网络(FCN)的高容量和快速计算的优势,设计了一个字符建议网络(CPN)。具体来说,该网络同时预测性格分数并细化相应的位置。特征分数可用于提案排名以拒绝非特征提案,并且细化过程旨在获得更准确的位置。此外,考虑到不同的字符具有不同的长宽比,我们提出了一种多模板策略,为每个长宽比设计一个细化器。实验结果表明,该方法在ICDAR 2013、SVT和Chinese 2k数据集上分别取得了93.88%、93.60%和96.46%的召回率,且建议数少于1000个,证明了该方法的良好性能。

英文摘要:

Maximally stable extremal regions (MSER), which is a popular method to generate character proposals/candidates, has shown superior performance in scene text detection. However, the pixel-level operation limits its capability for handling some challenging cases (e.g., multiple connected characters, separated parts of one character and non-uniform illumination). To better tackle these cases, we design a character proposal network (CPN) by taking advantage of the high capacity and fast computing of fully convolutional network (FCN). Specifically, the network simultaneously predicts characterness scores and refines the corresponding locations. The characterness scores can be used for proposal ranking to reject non-character proposals and the refining process aims to obtain the more accurate locations. Furthermore, considering the situation that different characters have different aspect ratios, we propose a multi-template strategy, designing a refiner for each aspect ratio. The extensive experiments indicate our method achieves recall rates of 93.88%, 93.60% and 96.46% on ICDAR 2013, SVT and Chinese2k datasets respectively using less than 1000 proposals, demonstrating promising performance of our character proposal network.

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。

↑