I'm creating an application that finds all of the text in a picture regardless of text size or font (whithin reason, Just the basic monospaced and default windows fonts). I tried making my own but it was slow and very unreliable. I need it to work fast (as close to instant (give or take 1 or 2 seconds)). I have to run it on images 1000+x1000+ (Nothing more than 1500). I have to take the values of the text and the position of it in the image.
Thanks if you can help!
I'm using VB.net, just so you know.
I suggest you look into the Tesseract OCR library (currently maintained by Google) which also has a .NET binding here and a related SO question here.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With