论文标题
漫画中的无约束文本检测：新数据集和基线
Unconstrained Text Detection in Manga: a New Dataset and Baseline
论文作者
论文摘要
对不受约束文本的检测和识别是研究中的一个空缺问题。漫画书中的文字具有不寻常的样式，可以引起文本检测的许多挑战。这项工作旨在以具有高度复杂的文本样式的漫画类型中的文本进行二进制：日本漫画。为了克服缺乏具有像素级别文本注释的漫画数据集，我们创建了自己的。为了改善对最佳模型的评估和搜索，除了二进制中的标准指标外，我们还实施了其他特殊指标。使用这些资源，我们设计并评估了一个深层网络模型，超过了大多数指标中漫画中文本二进制的当前方法。
The detection and recognition of unconstrained text is an open problem in research. Text in comic books has unusual styles that raise many challenges for text detection. This work aims to binarize text in a comic genre with highly sophisticated text styles: Japanese manga. To overcome the lack of a manga dataset with text annotations at a pixel level, we create our own. To improve the evaluation and search of an optimal model, in addition to standard metrics in binarization, we implement other special metrics. Using these resources, we designed and evaluated a deep network model, outperforming current methods for text binarization in manga in most metrics.
