Back to the Future of Handwriting Recognition (2016)

#1

Post by at1as » Mon, Aug 10, 2026, 3:58 PM UTC

Back to the Future of Handwriting Recognition (2016)
jackschaedler.github.io

Re: Back to the Future of Handwriting Recognition (2016)

#2

Post by dweisinger » Mon, Aug 10, 2026, 4:15 PM UTC

I can remember the early days of OCR and handwriting recognition. At that time, it was a difficult problem. Things have changed.

Re: Back to the Future of Handwriting Recognition (2016)

#3

Post by 392 » Mon, Aug 10, 2026, 4:51 PM UTC

dweisinger wrote: post #2

I can remember the early days of OCR and handwriting recognition. At that time, it was a difficult problem. Things have changed.

what is the state of the art now, that runs on-device? the article didn't mention the Q$ family, but I haven't found anything better than that plus mixing/co-judging with a dynamic-time-warping based approach

Re: Back to the Future of Handwriting Recognition (2016)

#4

Post by dcrazy » Mon, Aug 10, 2026, 6:34 PM UTC

Oh hey, it’s Graffiti! https://en.wikipedia.org/wiki/Graffiti_(Palm_OS)

Re: Back to the Future of Handwriting Recognition (2016)

#5

Post by criddell » Mon, Aug 10, 2026, 6:35 PM UTC

392 wrote: post #3

dweisinger wrote: post #2

I can remember the early days of OCR and handwriting recognition. At that time, it was a difficult problem. Things have changed.

what is the state of the art now, that runs on-device? the article didn't mention the Q$ family, but I haven't found anything better than that plus mixing/co-judging with a dynamic-time-warping based approach

I tried to search for Q$ but google returned no results. What is it?

For my handwriting, the ParaGraph engine inside Evernote worked perfectly. I believe it's the same system that the US postal service uses.

Re: Back to the Future of Handwriting Recognition (2016)

#6

Post by yubblegum » Mon, Aug 10, 2026, 6:35 PM UTC

That Alan Kay video is unreal. It took h/w and materials engineering a fairly long time to catch up with the visionaries.

Re: Back to the Future of Handwriting Recognition (2016)

#7

Post by WalterBright » Mon, Aug 10, 2026, 6:37 PM UTC

392 wrote: post #3

dweisinger wrote: post #2

I can remember the early days of OCR and handwriting recognition. At that time, it was a difficult problem. Things have changed.

what is the state of the art now, that runs on-device? the article didn't mention the Q$ family, but I haven't found anything better than that plus mixing/co-judging with a dynamic-time-warping based approach

I found that AI can even decipher Suetterlin! Oh well, so much for my secret handwriting.

Re: Back to the Future of Handwriting Recognition (2016)

#8

Post by oneearedrabbit » Mon, Aug 10, 2026, 8:35 PM UTC

criddell wrote: post #5

392 wrote: post #3

Earlier quoted context omitted.

what is the state of the art now, that runs on-device? the article didn't mention the Q$ family, but I haven't found anything better than that plus mixing/co-judging with a dynamic-time-warping based approach

I tried to search for Q$ but google returned no results. What is it? For my handwriting, the ParaGraph engine inside Evernote worked perfectly. I believe it's the same system that the US postal service uses.

https://depts.washington.edu/acelab/proj/dollar/qdollar.html

Re: Back to the Future of Handwriting Recognition (2016)

#9

Post by criddell » Mon, Aug 10, 2026, 9:09 PM UTC

oneearedrabbit wrote: post #8

criddell wrote: post #5

Earlier quoted context omitted.

I tried to search for Q$ but google returned no results. What is it? For my handwriting, the ParaGraph engine inside Evernote worked perfectly. I believe it's the same system that the US postal service uses.

https://depts.washington.edu/acelab/proj/dollar/qdollar.html

That looks pretty limited.