[tesseract-ocr] Re: Is it better to train tesseract with lager fontsize?

Try it? W dniu sobota, 17 stycznia 2015 07:12:38 UTC+1 użytkownik nahibi napisał: > > Hi, > > is it better to train tesseract with lager fontsize or should i train it > with the real fontsize? > > Which example is better? > > *example 1:* > fontsize (what i want to read with tesseract): 20 > font

[tesseract-ocr] Re: Digits recognition: tesseract vs. image moments

Tesseract is not a tool for you. Better look around OpenCV or similar. W dniu niedziela, 11 stycznia 2015 17:49:11 UTC+1 użytkownik Pavel Novikov napisał: > > Hello all > I'm new in tesseract, OCR and comple image recognition. Me and my > colleague are struggling into following problem: we need

[tesseract-ocr] Re: tessdata/eng.traineddata question

It should identify those images without any problems, you just need to prepare image right. 3 steps for you: 1. Tesseract likes when letters are about 70-100px height, so you need to resize your images. 2. Invert colors - as I noticed, it doesn't like it this way at all - letters must have to

[tesseract-ocr] Re: How do I make a dictionary from set of char images and characters corresponding to them?

PS. I tried to see what jTessBoxEditor does, but output traineddata doesn't seems to be correct... When I use it, application crashes with error: tessdata_manager.SeekToStart(TESSDATA_INTTEMP):Error:Assert failed:in file ..\..\classify\adaptmatch.cpp, line 555 Generated files attached. It is ca

[tesseract-ocr] How do I make a dictionary from set of char images and characters corresponding to them?

I got set of black and white images... a.png b.png c.png etc... How do I teach tesseract those characters into new dictionary? Best regards, FlashT -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop rece