Hacker News new | ask | show | jobs
by Qwertious 688 days ago
Well, that explains why I could never find a decent stroke-order-aware HWR system that wasn't a service. Sigh. What idiot invented this terminology?
1 comments

Yes, you're right, stroke-order-aware HWR are hard to find. One reason for that is the lack of good datasets for machine learning model training!

As such, my stroke-order-aware attempt over at https://github.com/PellelNitram/OnlineHTR/ uses a dataset from 2000 with around 12,000 samples. Contrary, the internal Google dataset is reported to feature around 16,000,000 samples :-D.