Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation

TL;DR

The paper tackles translating Manhwa from Indonesian to English to broaden accessibility. It introduces an end-to-end pipeline that detects speech bubbles with a fine-tuned YOLOv5xu, extracts text via Tesseract OCR, translates with MarianMT, and overlays the translation back onto panels. The approach is trained on a small Manhwa dataset and Indonesian–English parallel corpora (Identic/OpenSubtitles) and evaluated with standard metrics across detection, OCR, MT, and the full pipeline. Results show strong bubble detection, competitive OCR accuracy, and meaningful translations, indicating the viability of a multimodal, low-resource translation workflow and informing future dataset expansion and panel-level processing.

Abstract

In this project, we develop a practical and efficient solution for automating the Manhwa translation from Indonesian to English. Our approach combines computer vision, text recognition, and natural language processing techniques to streamline the traditionally manual process of Manhwa(Korean comics) translation. The pipeline includes fine-tuned YOLOv5xu for speech bubble detection, Tesseract for OCR and fine-tuned MarianMT for machine translation. By automating these steps, we aim to make Manhwa more accessible to a global audience while saving time and effort compared to manual translation methods. While most Manhwa translation efforts focus on Japanese-to-English, we focus on Indonesian-to-English translation to address the challenges of working with low-resource languages. Our model shows good results at each step and was able to translate from Indonesian to English efficiently.

Figures (3)

• Figure 1: Overview of Methodology
• Figure 2: Side-by-side comparison of the original panel and bounding box detection.
• Figure 3: Pipeline steps: (a) Enhanced speech bubbles, (b) Final translated panel, (c) OCR results, and (d) Translated text .