Towards Content-Aware Pixel-Wise Comic Panel Segmentation

Hikaru Ikuta, Runtian Yu, Yusuke Matsui, Kiyoharu Aizawa

Abstract: Comic panel detection is the task of identifying panel regions from a given comic image. Many comic datasets provide the borders of the panel lines as its panel region annotations, expressed in formats such as bounding boxes. However, since such panel annotations are usually not aware of the contents of the panel, they do not capture objects that extend outside of the panels, causing such objects to be partially discarded when panels are cropped along the annotations. In such applications, a content-aware annotation that contains all of the contents in each panel is suitable. In this paper, we assess the problem of content-aware comic panel detection using two types of annotations. We first create a small dataset with bounding box annotations where each region contains the entire contents of each panel, and train a detection model. We also explore training a pixel-wise instance segmentation model using synthetic data.