• 0 Posts
  • 365 Comments
Joined 11 months ago
cake
Cake day: August 8th, 2023

help-circle
  • How good is good do you say?

    We got a pretty good results with CER at 4% and WER at 15%!

    This was on a limited dataset used to test and train which most likely means that if you introduced an even larger dataset with greater variations in handwriting style for testing the numbers might be even worse.

    Very simplified: A risk of a character wrong every 20th character and a word wrong every 7th word. The SER was around 20%.

    There’s an reason why no one has released a good model for western letters yet and why companies pay up to 1€ for capturing data from 10 handwritten pages.

    It will come but OCR isn’t as sexy as developing text2image solutions.






  • To train an AI to recognize handwriting you need a huge dataset of handwriting examples. That is millions of samples of handwritten text + information about what the written text says in every example).

    This is why the best engines only exists as a service in the cloud. The OCR engines you can install lovely that are acceptable, but far from perfect, are commercial. Parascript FormXtra is one of the better commercial ones.

    The only OCR Engine that’s free and really good is Tesseract OCR but it doesn’t handle handwritten text.






  • Please elaborate and feel free to edit Wikipedia:

    On 8 October 2023, the Lebanese militant group Hezbollah, taking advantage of the Israel–Hamas war, fired guided rockets and artillery shells at Israeli positions in the occupied Shebaa Farms. Israel retaliated by launching drone strikes and artillery shells at Hezbollah positions near Lebanon’s boundary with the Israeli-occupied Golan Heights. The outbreak of the conflict had followed Hezbollah’s declaration of support and praise for the Hamas attack on Israel, which took place on 7 October.