Live data from Hacker News

UK scientists ask for help in transcribing 200 years of rainfall data

bbc.com

1–10 of 43 posts

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#4
post #3

Why hasn't this been automated? Digit recognition technology is pretty good and it seems like the forms are pretty standardized.

Probably because 99% accuracy isn't good enough.

What accuracy do you think humans have?

If I give you 1000 handwritten numbers, do you think you'll make less than 10 mistakes?

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#5
post #3

Why hasn't this been automated? Digit recognition technology is pretty good and it seems like the forms are pretty standardized.

Probably because 99% accuracy isn't good enough.

Haha 99% accuracy in weather data would be an amazing improvement. Noisy data and data holes are all we got to work with. Humidity sensors have a memory, storing moist/dry air inside the ceramic.

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#6
post #3

Earlier quoted context omitted.

Probably because 99% accuracy isn't good enough.

What accuracy do you think humans have? If I give you 1000 handwritten numbers, do you think you'll make less than 10 mistakes?

They will likely assign the same tasks to multiple people and use an ensemble of human consensus.

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#7
post #3

Earlier quoted context omitted.

Probably because 99% accuracy isn't good enough.

What accuracy do you think humans have? If I give you 1000 handwritten numbers, do you think you'll make less than 10 mistakes?

Run both OCR and human in parallel and double check anomalies

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#9
post #3

Why hasn't this been automated? Digit recognition technology is pretty good and it seems like the forms are pretty standardized.

Probably because 99% accuracy isn't good enough.

Checking the results of OCR is a lot faster than manually doing the OCR, no?

Re: UK scientists ask for help in transcribing 200 years of rainfall data

#10
post #3

Why hasn't this been automated? Digit recognition technology is pretty good and it seems like the forms are pretty standardized.

Probably because 99% accuracy isn't good enough.

I've had a look at a few of those and I doubt you'd get 99% accuracy. A lot of the footnotes especially are very hard to decipher. They're also 50 years old, handwriting has changed over time. I'm not sure how well models are trained to read old handwriting, I know that I struggle with it.

For humans, much can be deciphered through context. That's much more complex to do with OCR.

Post reply on HN