arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.06508cs.CV
收藏

基于二维的视角的场景文本识别

Scene Text Recognition from Two-Dimensional Perspective

Huazhong University of Science and Technology(华中科技大学);Megvii (Face++)(旷视(Face++))

Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, Xiang Bai

摘要:

受语音识别的启发,目前的最新算法大多将场景文本识别视为序列预测问题。虽然这些方法取得了很好的性能,但通常忽略了一个重要的事实,即图像中的文本实际上是分布在二维的【形】空间中。它的性质与语音的性质完全不同,语音本质上是一维信号。原则上,直接将文本的特征压缩成一维形式可能会丢失有用的信息并引入额外的噪声。在本文中,我们从二维的【形】角度来处理场景文本识别。提出了一种简单有效的字符注意力全卷积网络(CA-FCN)模型,用于识别任意形状的文本。场景文本识别采用语义分割网络实现,其中采用了字符的注意力机制。结合一个构词模块,CA-FCN可以同时识别脚本和预测每个字符的位置。实验结果表明,该算法在规则和不规则文本数据集上的性能都优于以往的方法。此外,它被证明是更强大的文本检测阶段,这是非常常见的不精确的本地化。

英文摘要:

Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in images are actually distributed in two-dimensional space. It is a nature quite different from that of speech, which is essentially a one-dimensional signal. In principle, directly compressing features of text into a one-dimensional form may lose useful information and introduce extra noise. In this paper, we approach scene text recognition from a two-dimensional perspective. A simple yet effective model, called Character Attention Fully Convolutional Network (CA-FCN), is devised for recognizing the text of arbitrary shapes. Scene text recognition is realized with a semantic segmentation network, where an attention mechanism for characters is adopted. Combined with a word formation module, CA-FCN can simultaneously recognize the script and predict the position of each character. Experiments demonstrate that the proposed algorithm outperforms previous methods on both regular and irregular text datasets. Moreover, it is proven to be more robust to imprecise localizations in the text detection phase, which are very common in practice.

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。

↑