Awesome

Quantifying-Character-Similarity

This repo includes

• Tutorials: notebook
• Homoglyphs Dictionaries: Simplified Chinese, Traditional Chinese, Japanese, Korean.
• CJK Fonts are here.
• Scripts for japanese supply chain matching
• Scripts for Synthetic Chinese, Japanese, Korean placenames matching
• Scripts for ViT training and Inference for homoglyphs dicts: coming soon...
• Scripts for ViT training and Inference for Ancient Chinese: coming soon...

For the Ancient Chinese Character Dataset:

• Meta data file: coming soon..
• Ancient Chinese Character Images: We draw our character images from https://xiaoxue.iis.sinica.edu.tw/yanbian
• Folder of visualization: coming soon..