본문 바로가기

SickZil-machine: A deep learning based script text isolation system for comics translation

문서 유형
연구출판물 · 학술대회 발표논문
등재
Scopus
저널 순위
Scopus Q2
저널
Lecture Notes in Computer Science12116 LNCS · pp.413 · 2020
피인용
Scopus 5
FWCI (Scopus)
0
ISSN
0302-9743

저자

  1. 고우람제1저자Department of Electrical and Computer Engineering, Pusan National University, Pusan, South Korea
  2. 조환규교신저자Department of Electrical and Computer Engineering, Pusan National University, Pusan, South Korea

초록

The translation of comics (and Manga) involves removing text from a foreign comic images and typesetting translated letters into it. The text in comics contain a variety of deformed letters drawn in arbitrary positions, in complex images or patterns. These letters have to be removed by experts, as computationally erasing these letters is very challenging. Although several classical image processing algorithms and tools have been developed, a completely automated method that could erase the text is still lacking. Therefore, we propose an image processing framework called ‘SickZil-Machine’ (SZMC) that automates the removal of text from comics. SZMC works through a two-step process. In the first step, the text areas are segmented at the pixel level. In the second step, the letters in the segmented areas are erased and inpainted naturally to match their surroundings. SZMC exhibited a notable performance, employing deep learning based image segmentation and image inpainting models. To train these models, we constructed 285 pairs of original comic pages, a text area-mask dataset, and a dataset of 31,497 comic pages. We identified the characteristics of the dataset that could improve SZMC performance. SZMC is available at: https://github.com/KUR-creative/SickZil-Machine. © Springer Nature Switzerland AG 2020.

키워드

Comics translationDeep learningImage manipulation system

식별자

Scopus EID
2-s2.0-85090098326