How Panel Layouts Define Manga: Insights from Visual Ablation Experiments

TL;DR

This study investigates how manga panel layouts contribute to the unique identity of manga works by using deep learning and ablation experiments to analyze visual features and demonstrate their significance.

Contribution

It introduces a quantitative and qualitative analysis method focusing on panel layouts, revealing their strong influence on manga uniqueness.

Findings

Panel layouts significantly reflect manga uniqueness.

Deep learning models can classify manga based on panel layout features.

Ablation studies highlight the importance of panel framing in manga identification.

Abstract

Today, manga has gained worldwide popularity. However, the question of how various elements of manga, such as characters, text, and panel layouts, reflect the uniqueness of a particular work, or even define it, remains an unexplored area. In this paper, we aim to quantitatively and qualitatively analyze the visual characteristics of manga works, with a particular focus on panel layout features. As a research method, we used facing page images of manga as input to train a deep learning model for predicting manga titles, examining classification accuracy to quantitatively analyze these features. Specifically, we conducted ablation studies by limiting page image information to panel frames to analyze the characteristics of panel layouts. Through a series of quantitative experiments using all 104 works, 12 genres, and 10,122 facing page images from the Manga109 dataset, as well as qualitative analysis using Grad-CAM, our study demonstrates that the uniqueness of manga works is strongly reflected in their panel layouts.