DaKanji Single Kanji Recognition

This CNN can recognize a single character (Kanji, Hiragana, Katakana). A list of all supported characters can be found here.

Apps which use this model

name	android	iOS	Linux	MacOS	Windows	Web
DaKanji	✅		✅	✅	✅
Kanji Graph	✅

Training

To generate the data necessary to train this CNN, the single_kanji_data_gen notebook is used. The training can than be done with the single_kanji_cnn_training notebook.

Inference

In the releases section pretrained model weights can be found. Also a TensorFlow lite model is available.

Input: The input should be a grayscale image of any size.

Output: A one-hot-vector containing the class probabilities (lines up with labels.txt).

Setup development environment

install all dependencies:

python -m pip install wheel
python -m pip install -r requirements.txt

Now you should follow model specific setup steps. For this look at the README for the model you are interested in.

Usage in your software

I put lots of effort and time into developing this model and hope that it can be used in many apps. If you decide to use this machine learning model please give me credit like: Character recognition powered by machine learning from CaptainDario (DaAppLab) It would also be nice if you open an issue and tell me that you are using this model. Than I would add your software to the test

Credits

The data on which the neural network was trained on was kindly provided by ETL Character Database

The KanjiVG dataset was used to generate "handwritten" kanjis Papers:

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Recognizing Handwritten Japanese Characters Using Deep Convolutional Neural Networks
• A neural framework for online recognition of handwritten Kanji characters
• Online Handwritten Kanji Recognition Based on Inter-stroke Grammar