How the US Postal Service reads terrible handwriting
Tom Scott4 HN recommenders · recommended in 3 months, 2022-2026
7M views · 4 years ago · documentary · evergreen
Tom Scott visits the USPS Remote Encoding Center in Salt Lake City, where keyers decipher mail images machines cannot read. It shows the lengths taken to decode bad handwriting.
Recommended in address and OCR threads as a look at the last human mail-coding operation.
23:39I sent robot forgeries to a handwriting expert
Stuff Made Here
11.5M views • 3 years ago
11:25The Worst Typo I Ever Made
Tom Scott
6.4M views • 6 years ago
35:49Breaking The Creepy AI in Police Cameras
Benn Jordan
3.8M views • 1 year ago
1:00BFS-Auto: High Speed Book Scanner at over 250 pages/min
Ishikawa Group Laboratory
1.3M views • 13 years ago
4:31why typing like this is sometimes okay.
Tom Scott
5.4M views • 7 years ago
24:13Uppestcase and Lowestcase Letters [advances in derp learning]
suckerpinch
477K views • 5 years ago
20:39AI Language Models & Transformers - Computerphile
Computerphile
354K views • 7 years ago
12:01Why Electronic Voting Is Still A Bad Idea
Tom Scott
5.1M views • 6 years ago
8:21Why Electronic Voting is a BAD Idea - Computerphile
Computerphile
2.3M views • 11 years ago
15:49I tried using AI. It scared me.
Tom Scott
8.5M views • 3 years ago
13:30Stealing Baseball Signs with a Phone (Machine Learning)
Mark Rober
30M views • 7 years ago
2:13:35Let's build the GPT Tokenizer
Andrej Karpathy
1.3M views • 2 years ago
3:37Why Web Filters Don't Work: Penistone and the Scunthorpe Problem
Tom Scott
3.6M views • 10 years ago
13:52Ch(e)at GPT? - Computerphile
Computerphile
617K views • 3 years ago
6:16The Artificial Intelligence That Deleted A Century
Tom Scott
2M views • 7 years ago
8:30Deadly Truth of General AI? - Computerphile
Computerphile
941K views • 11 years ago
17:15The Art of the Bodge: How I Made The Emoji Keyboard
Tom Scott
3.5M views • 11 years ago
10:34Windows Vista Speech Recognition Tested - Perl Scripting
scrubadub1
913K views • 19 years ago
19:29Glitch Tokens - Computerphile
Computerphile
353K views • 3 years ago
28:48LSTM is dead. Long Live Transformers!
Seattle Applied Deep Learning
540K views • 6 years ago
8 comments from Hacker News
As a profession (and under time constraints) ... Tom Scott : How the US Postal Service reads terrible handwriting - ▶ this video Part of the story is that the OCR that is handling hand lettered addresses. I also chuckled at the cursive letter recognition sheet on the side of the cube.
> Though USPS has been doing handwriting recognition since the 80's. On a very restricted dictionary of possible content, with a pool of people employed to fix anything where the computer is unsure. ▶ this video
And like almost all things that are interesting, here's a Ton Scott video about the same topic: ▶ this video
Tom Scott did a great video showing the last one in operation. They use totally unique keyboards with what is essentially a stenography system: ▶ this video
This Tom Scott video shows some of the surprising (to me) lengths to which the USPS does go to figure out the right address: ▶ this video Obviously this doesn't apply to your case, but I certainly didn't think they'd have a national center for decoding terrible handwriting.
▶ this video might be of interest - it has some of what the machines are trying to read and what accuracy they need.
One of Don Rosa's books has the letters he sent to a friend in college, each with a drawing on the envelope and less and less address, until finally it was all drawing and barely part of a name - they all got (eventually) delivered. There's a specific branch of the post office that works on these - the dead letter office: ▶ this video
Actually, we're talking about both, and you are wrong on both counts. If you weren't, you would be able to point to an existing system that has demonstrated the capability of classifying an image set on the order of iCloud's, without producing a false-positive. You can't, because such a system doesn't exist. Even the "solved" problem of OCR isn't capable of such a feat: ▶ this video