
Evaluate the performance of OCR on Japanese text images.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
1
±0 (Oct 13〜)
Last commit
Mar 2024
Created on GitHub
Mar 9, 2024
Listed
Oct 7, 2025
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 1 |
| Jan 2026 | 1 |
| Feb 2026 | 1 |
| Mar 2026 | 1 |
| Apr 2026 | 1 |
| May 2026 | 1 |
| Jun 2026 | 1 |
| Jul 2026 | 1 |
| Aug 2026 | 1 |
| Sep 2026 | 1 |
| Oct 2026 | 1 |
| Nov 2026 | 1 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
manga-ocrkha-white2.8kAbout Optical character recognition for Japanese text, with the main focus being Japanese manga
mokurokha-white1.8kRead Japanese manga inside browser with selectable text.
yomitokukotaro-kinoshita1.7kYomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
meikipoprtr46734universal japanese ocr popup dictionary for windows, linux and macos
Poricomblueaxis447Optical character recognition in manga images. Manga OCR desktop application
owocraurorawright317Optical character recognition for Japanese text
Resources in similar research fields
meikiocrrtr46103high-speed, high-accuracy, local ocr for japanese video gamesShared: Visual Data in NLP
MangaOCRgnurt204140A lightweight OCR model for Japanese text, especially in MangaShared: Visual Data in NLP
paddleocr-vl-sft-for-japanese-manga-on-rtx-3060openvino-book16Fine-tune PaddleOCR-VL on the Manga109s dataset for Japanese manga text recognition. The base model struggles with vertical Japanese text reading order in manga. After fine-tuning, the model correctly handles manga-specific text layouts.Shared: Visual Data in NLP- manga-ocr-basekha-white299kManga OCR is a Vision Encoder‑Decoder OCR tool that reads vertical and horizontal Japanese manga text—including furigana—across diverse fonts and low‑quality images, with the source code freely available.HF modelShared: Visual Data in NLP
- meiki.txt.recognition.v0rtr4642kMeikiocr’s meiki.text.recognition.v0—a D‑FINE-based MobileNetV4 model fine‑tuned on Japanese video‑game text—delivers state‑of‑the‑art accuracy and latency for horizontal text by detecting up to 48 characters from 960×32 inputs, outputting each character with its bounding box and confidence score.HF modelShared: Visual Data in NLP
- meiki.text.detect.v0rtr4622kmeikiocr supplies a D‑FINE‑based, open‑weight text‑detection model for video‑games (v0.1 with MobileNet‑v4 backbones, two resolution variants and a 64‑box limit) and experimental low‑latency tiny and small variants trained on Japanese video‑games and manga.HF modelShared: Visual Data in NLP