Hi,
Here's the point: I have to train tesseract on a new font in traditional
chinese. For now, all the results were not good enough.
I've just tried to train it with only a small set of characters and 1 input
image.
Then I took a sample of that image to test it.
The image is:
And the detected text is: 客戶服務 置龍擇語言 設交置 社交
I'm using tesseract 3.02 on Windows.
The questions are:
- What kind of machine learning concept tesseract use ?
- How can I have better results with tesseract ?
- Do I have to train it with a lot of different images ?
- Do I have some parameters to play with on the training part ?
Thanks.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/5ca02ec4-14ef-4a39-8a01-252142894cf2%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
