A Method to Annotate Who Speaks a Text Line in Manga and Speaker-Line Dataset for Manga109

Speaker estimation in a manga is one of the components that needs to be recognized in conducting research using manga. To identify the speaker of a text line in a manga, a dataset of who speaks the lines is needed. In order to construct such a dataset easily, we proposed a method to annotate who speaks a text line based on characteristics of information design and the human factor. Then, we developed a prototype system and constructed a dataset that mapped between text lines and speakers in the Manga109 dataset and distributed the dataset on the Web. In addition, we analyzed the dataset and showed that the perfect match rate was about 80% when there were five annotators. It was also found that variation in annotation occurred even with human judgment and that this was partly due to lines requiring reference to other frames. We also found that it was difficult for annotators to map speakers in scenes involving science fiction and battles by calculating the Evaluation Consistency Indicators.