Synth-JDoc: Synthesizing a Japanese Document Image Dataset for OCR with Diverse Layouts and Embedded Images

The paper introduces Synth-JDoc, a synthetic Japanese document image dataset created by rendering text with HTML and CSS to produce multi‑column layouts that include both vertical and horizontal writing styles. Images generated by text‑to‑image models are embedded to enhance visual realism, and noise and degradation filters are applied to improve robustness. Experiments show that fine‑tuning Large Vision Language Models on Synth‑JDoc yields superior performance on reading vertically written Japanese text compared to prior synthetic datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• diffusion
• computer-vision
• nlp
• fine-tuning