I'm trying to use Tesseract on Android, and the results I'm getting aren't
too good. Attempt 1 was to recognize the words "Simple text" in a very
simple png (white on black). It came up with garbage. I then tried a
random jpeg on the internet, it recognized about 50% of words. My final
trial was a playing card (4 of diamonds). It came back with "9 9" then
garbage. I could see it confusing the 4s with 9s, but theres no reason for
the garbage. I would think that's a very simple test for it- just 4
characters, lots of whitespace between them.
I'm using the tesseract-android-tools library. Is there a way to improve
things so I can get some better results? Here's my exact code:
TessBaseAPI baseApi = new TessBaseAPI();
baseApi.setDebug(true);
baseApi.init(getFilesDir()+"/", "eng");
baseApi.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST,
"2345678910KJQA");
baseApi.setVariable(TessBaseAPI.VAR_ACCURACYVSPEED, "100");
baseApi.setVariable("tessedit__numeric_mode", "1");
baseApi.setImage(new File(getFilesDir(), "image.png"));
String recognizedText = baseApi.getUTF8Text();
baseApi.end();
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
---
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].
For more options, visit https://groups.google.com/groups/opt_out.
