CVMMMar 23, 2018

Object Detection for Comics using Manga109 Annotations

arXiv:1803.08670v257 citations
AI Analysis

This work addresses the problem of object detection in digitized comics for researchers and developers, but it is incremental as it builds on existing CNN-based methods with specific adaptations.

The paper tackled object detection in comics by addressing the lack of large-scale annotated datasets and the challenge of highly overlapped objects, resulting in the creation of the Manga109-annotations dataset and the SSD300-fork model, which outperformed other methods based on mAP scores.

With the growth of digitized comics, image understanding techniques are becoming important. In this paper, we focus on object detection, which is a fundamental task of image understanding. Although convolutional neural networks (CNN)-based methods archived good performance in object detection for naturalistic images, there are two problems in applying these methods to the comic object detection task. First, there is no large-scale annotated comics dataset. The CNN-based methods require large-scale annotations for training. Secondly, the objects in comics are highly overlapped compared to naturalistic images. This overlap causes the assignment problem in the existing CNN-based methods. To solve these problems, we proposed a new annotation dataset and a new CNN model. We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations. For the assignment problem, we proposed a new CNN-based detector, SSD300-fork. We compared SSD300-fork with other detection methods using Manga109-annotations and confirmed that our model outperformed them based on the mAP score.

Code Implementations5 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes