CCC - Cursive Character Challenge
This is the home page of Cursive Character Challenge (C-Cube), the new benchmark for machine learning and pattern recognition algorithms. The database contains 57293 cursive characters manually extracted from cursive words, including both upper and lower case versions of each letter.
The database is split into:
- training set (38160 characters)
- test set (19133 characters)
The full database description and the download can be found here: CCC