Skip to main content

handwritten kanji recognition

Project description

GitHub Release PyPI Version Python Versions CI AGPLv3+ Sponsor

kanjidraw - handwritten kanji recognition

kanjidraw is a simple Python library + GUI for matching (the strokes of a) handwritten kanji against its database.

You can use the GUI to draw and subsequently select a kanji from the list of probable matches, which will then be copied to the clipboard.

The database is based on KanjiVG and the algorithms are based on the Kanji draw Android app.

Library

For a JavaScript frontend example, see e.g. jiten's kanjidraw.js.

Requirements

  • Python >= 3.5 (w/ Tk support for the GUI).

Debian/Ubuntu

$ apt install python3-tk

Installing

Using pip

$ pip install kanjidraw

NB: depending on your system you may need to use e.g. pip3 --user instead of just pip.

From git

NB: this installs the latest development version, not the latest release.

$ git clone https://github.com/obfusk/kanjidraw.git
$ cd kanjidraw
$ pip install -e .

NB: you may need to add e.g. ~/.local/bin to your $PATH in order to run kanjidraw.

To update to the latest development version:

$ cd kanjidraw
$ git pull --rebase

License

Code

© Felix C. Stegerman

AGPLv3+

KanjiVG (stroke data)

© Ulrich Apel

CC-BY-SA

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kanjidraw-0.2.0.tar.gz (515.9 kB view hashes)

Uploaded Source

Built Distribution

kanjidraw-0.2.0-py3-none-any.whl (540.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page