The Writing Is on the Wall for Handwriting Recognition

coolness an hour ago | parent | next [-]

Great post and amazing progress in this field! However, I have to wonder if some of these letters were part of the training data for Gemini, since they are well-known and someone has probably already done the painstaking work of transcribing them...

	▲	suddenlybananas an hour ago \| parent [-]
		Shhhhh no one cares about data contamination anymore.

▲

pjmlp 29 minutes ago | parent | prev | next [-]

Maybe for English, for the other human languages I use, it is still kind of hit and miss, just like speaking recognition, even with English it suffices to have an accent that is off the standard TV one.

	▲	NitpickLawyer 19 minutes ago \| parent [-]
		ee lay vhen!

▲

__alexs 29 minutes ago | parent | prev | next [-]

Call me when it can do Russian Cursive.

	▲	decimalenough 15 minutes ago \| parent [-]
		Seems to do an OK job: https://g.co/gemini/share/e173d18d1d80 This is a random image from Twitter with no transcript or English translation provided, so it's not going to be in the training data.

▲

iamflimflam1 38 minutes ago | parent | prev | next [-]

If I went back in time to the 90s when I was doing my PhD I would absolutely blow my mind with how well handwriting OCR works now.

▲

th0ma5 37 minutes ago | parent | prev [-]

My question for OCR automation is always which digits within the numbers being read are allowed to be incorrect?