COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
复制标题
DOI：
10.48550/arxiv.2207.04675
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Jeonghun Baek;Yusuke Matsui;K. Aizawa
中科院分区：
文献类型：
--
作者：
Jeonghun Baek;Yusuke Matsui;K. Aizawa
识别不规则文本一直是文本识别中的一个具有挑战性的课题。为了鼓励这一主题的研究，我们提供了一个新颖的漫画拟声词数据集（COO），其中包含日本漫画中的拟声词文本。 COO 有许多任意文本，例如极度弯曲、部分收缩的文本或任意放置的文本。此外，有些文本被分成几个部分。每个部分都是被截断的文本，本身没有任何意义。这些部分应该链接起来以代表预期的含义。因此，我们提出了一项新任务来预测截断文本之间的链接。我们执行三项任务来检测拟声词区域并捕获其预期含义：文本检测、文本识别和链接预测。通过大量的实验，我们分析了COO的特征。我们的数据和代码可在 \url{https://github.com/ku21fan/COO-Comic-Onomatopoeia} 获取。
Recognizing irregular texts has been a challenging topic in text recognition. To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consists of onomatopoeia texts in Japanese comics. COO has many arbitrary texts, such as extremely curved, partially shrunk texts, or arbitrarily placed texts. Furthermore, some texts are separated into several parts. Each part is a truncated text and is not meaningful by itself. These parts should be linked to represent the intended meaning. Thus, we propose a novel task that predicts the link between truncated texts. We conduct three tasks to detect the onomatopoeia region and capture its intended meaning: text detection, text recognition, and link prediction. Through extensive experiments, we analyze the characteristics of the COO. Our data and code are available at \url{https://github.com/ku21fan/COO-Comic-Onomatopoeia}.