# Unconstrained Text Detection in Manga: a New Dataset and Baseline

arXiv: https://arxiv.org/abs/2009.04042 · HTML: https://mlsanity.com/paper/2009.04042/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://mlsanity.com/paper/2208.00438/) (2022)
- [A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition](https://mlsanity.com/paper/2212.14674/) (2022)
- [RetriBooru: Leakage-Free Retrieval of Conditions from Reference Images for Subject-Driven Generation](https://mlsanity.com/paper/2312.02521/) (2023)
- [Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga](https://mlsanity.com/paper/2410.05935/) (2024)
- [Context-Informed Machine Translation of Manga using Multimodal Large Language Models](https://mlsanity.com/paper/2411.02589/) (2024)
- [Detection of Furigana Text in Images](https://mlsanity.com/paper/2207.03960/) (2022)

## Abstract (arXiv)

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.