Hacker News new | past | comments | ask | show | jobs | submit login

Interestingly, it interprets each pen stroke in the context of the wider piece of music, and makes use of temporal information such as the order the strokes are made in. Whereas classic OCR would just try and interpret the static 'picture':

Key to the way StaffPad works is its method of recognizing your scribbles. It looks at every individual stroke you make and then interprets what you wrote based on the relationship of each stroke to all of the others. David says that “it’s more efficient and accurate to take the position and temporal information from the pen, and then use musical context to decide what the music is trying to be. That way, you can do things that would totally confuse OCR. Because we know the order of the strokes and where they are in relation to the notes, we can say, OK, that’s a natural, that’s a sharp.”

http://www.sibeliusblog.com/news/staffpad-is-a-music-handwri...




Fascinating - wonder if this is similar to how a Korean phoneme or an ideogram is assembled while typing.


Similar to how Chinese characters are written: with a prescribed stroke order learnt at school.


No - I understand that part - I meant the transformation of the syllable as it is assembled. It changes shape in a similar way.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: