rtr46/meikiocr
high-speed, high-accuracy, local ocr for japanese video games
MeikiOCR helps you quickly and accurately extract Japanese text directly from images of video games or other rendered content. You provide an image with Japanese text, and it gives you the recognized text. This is perfect for localizers, fan translators, content creators, or anyone needing to capture text from Japanese video games.
Available on PyPI.
Use this if you need to reliably pull Japanese text from video game screenshots or similar highly stylized rendered digital content, and want a fast, private, and local solution.
Not ideal if you need to recognize handwritten Japanese text, text from complex real-world photographs, or if your images contain more than 64 lines of text or very long lines (over 48 characters) that need to be captured accurately.
Stars
63
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/rtr46/meikiocr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huoyijie/AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on...
argman/EAST
A tensorflow implementation of EAST text detector
HusseinYoussef/Arabic-OCR
OCR system for Arabic language that converts images of typed text to machine-encoded text.
HsiehYiChia/Scene-text-recognition
Scene text detection and recognition based on Extremal Region(ER)
SachaIZADI/Seven-Segment-OCR
Computer vision project to automatically recognize digits characters in a seven-segments display