←back to thread

386 points italophil | 6 comments | | HN request time: 0.001s | source | bottom
Show context
WhyOhWhyQ ◴[] No.46224941[source]
Is Calibri actually more accessible? Every step of this story seems pointless and fake.
replies(5): >>46224996 #>>46225153 #>>46225174 #>>46225199 #>>46225226 #
papercrane ◴[] No.46224996[source]
One of the reasons Calibri was selected over Times New Roman was it has a lower rate of OCR transcription errors, making documents using it easier for people using screen readers.
replies(2): >>46225285 #>>46227403 #
1. blueflow ◴[] No.46225285[source]
Link on that, as OCR should be more reliable with Times New Roman due to significant serifs.
replies(3): >>46225527 #>>46226162 #>>46227942 #
2. papercrane ◴[] No.46225527[source]
The memo at the time said the serifs can cause OCR issues.

https://x.com/John_Hudson/status/1615486871571935232

replies(1): >>46226222 #
3. orwin ◴[] No.46226162[source]
I don't have link on that, but the main difficulty with OCR isn't the OCR part (not anymore at least), it's the "clean up" part, and serifs are a pain in the ass, especially on sightly crumpled paper. My use case was an ERP plugin that digitalized and read to receipt to autofill reimbursement demands, and since most receipt use sans-serif fonts, it was mostly fine, but some jokers use serifed font (mostly on receipts you get when using cash, not credit card receipts) and the error rate jumped from like 1% to 13% (not sure about the 1%, it might be a story i told myself to make me feel better, it was a decade ago, before i pivoted to network from AI. I always take the best decision it seems)
4. opo ◴[] No.46226222[source]
Just because they claimed it, doesn't make it true. OCR and screen reader software in 2023 did not have problems with serifs.
replies(1): >>46226543 #
5. ◴[] No.46226543{3}[source]
6. nerevarthelame ◴[] No.46227942[source]
I don't know what studies Blinken's State Department considered, but here are 2 studies on the matter.

https://www.academia.edu/72263493/Effect_of_Typeface_Design_...: "For Latin, it was observed that individual letters with serif cause misclassification on (b,h), (u,n), (o,n), (o,u)."

https://par.nsf.gov/servlets/purl/10220037: [Figure 5 shows higher accuracy for the two sans-serif fonts, Arial and DejaVu compared to Times New Roman, across all OCR engines]