Japanese Character Classification
Project Scope:
This project is designed to take image recognition of Japanese characters, and create a learning model that can classify the characters based on the read input.
The project looks to accurately predict across the three main Japanese language writing systems (Kanji, Hiragana, Katakana) - used in Japan for over a thousand years since the 8th century.
The data is from the ETL Character Database, which includes over a billion total of Japanese characters hand-written and reorganized by the National Institute of Advanced Industrial Science and Technology (AIST).