I would like to get the code for tesseract confidence level. Any sample
code available ?
--
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
baseApi.init(filesDir.getPath() + /tesseract/, LANG);
baseApi.setPageSegMode(TessBaseAPI.PageSegMode.PSM_SINGLE_BLOCK);
baseApi.setImage(bmp);
OCRResult result = new OCRResult(baseApi.getUTF8Text(),
baseApi.meanConfidence());
baseApi.end();
Note OCRResult is my own object for holding values.
I couldn't find a detailed documentation and I don't feel browsing the
source code. I want not to redo canny edge detection for example if it is
already done by Tesseract engine. I need to know its steps before doing mine
--
You received this message because you are subscribed to the Google
Hi all,
Apologies for resurrecting an old thread, but I ran into the same issue and
have documented a workaround in this blog
post:
http://ryanfb.github.io/etc/2014/11/19/installing_tesseract_training_tools_on_mac_os_x.html
And the associated modified Homebrew
formula:
Hi Art Rhyno, Thanks for your response. I will check it..
On Wednesday, November 19, 2014 5:42:56 AM UTC+5:30, Art Rhyno wrote:
Shall I first crop the specific portion of the image to different
rectangles and then OCR them individually..?
Hi Vinay,
If you are getting better OCR results
Thanks Allistair for replying. I have a wide variety of invoice types which
are of no particular type. But all the invoice types will have the
necessary fields that I have mentioned earlier in my post but they may
exist at different locations in the image. Our solution should be able to
I'm dealing with font subsets, and I generate an image per font, so there
is no reading order. Though I've seen latin and cjk in the same font
subset. If OSD just gives, reading, orientation, and text order, it is not
going to give me anything useful. Plus I have the font, so I could get some
7 matches
Mail list logo
