[tesseract-ocr] Re: Reading handwritten subscripts and superscripts in tesseract

When I recently installed my version of tesseract, one of the language options was "Math / equation detection module". Have you tried that yet? On Wednesday, January 4, 2017 at 12:10:58 AM UTC-7, Sampurn Rattan Jain wrote: > > I want to read handwritten mathematical equations, which will not

[tesseract-ocr] how can tessbaseapi read config bazaar file and use user_words file in ANDROID?

Everything is set and working and ocr does a very good job. But I want to use special dictionary in ANDROID app. I am familiar with the method here ... https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#config-files-and-augmenting-with-user-data .. but it

Re: [tesseract-ocr] Re: Tesseract v3.03 and norwegian language

Tried 'Finetune' - that does not help in addition of a character. Trying 'Add a layer' now. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Thu, Jan 5, 2017 at 8:59 PM, Ludvig F Aarstad wrote: >

Re: [tesseract-ocr] Re: Tesseract v3.03 and norwegian language

Fantastic, 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to

Re: [tesseract-ocr] SetVariable on whitelist but get no luck

In master there is tesseract 4.0 and cube was removed from it (see e.g. [1]). So setting OEM_CUBE_ONLY has no effect. [1] https://github.com/tesseract-ocr/tesseract/commit/5c3839bdb42aa45c8d028e533eb0c1d3c9051b06 Zdenko On Thu, Jan 5, 2017 at 2:22 PM, Matthew Scott

Re: [tesseract-ocr] SetVariable on whitelist but get no luck

I build it from the master branch but not 3.05 however when using 'OEM_CUBE_ONLY`, the satVariable do work. 在 2017年1月5日星期四 UTC+8下午4:17:48，zdenop写道： > > OEM_LSTM_ONLY in tesseract 3.05[1]? Really??? > > [1] > https://github.com/tesseract-ocr/tesseract/blob/3.05/ccstruct/publictypes.h#L256 > >

Re: [tesseract-ocr] Re: Tesseract v3.03 and norwegian language

I will give it a try and let you know. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send

[tesseract-ocr] Re: Preprocessing ideas besides cropping/resizing/thresholding and identifying individual letters.

In the case of computer generated characters of fixed width and original resolution an exact comparison may also work. I did this 10 years ago for automatically testing the Debian installer in a virtual machine: - run the VM in X11-window - take a screenshot of the window - cut out the

Re: [tesseract-ocr] Re: Tesseract v3.03 and norwegian language

I can come up with several samples, if that helps. I also realized that the occurrence of Æ in the beginning of a sentence is quite rare. It will in most cases only be for names of people (surnames mostly) and names of places and streets in addition to some specific Norwegian words that can

[tesseract-ocr] SetVariable on whitelist but get no luck

version: 3.05 //I compiled the tesseract305.dll system: windows 10 x64 I want to only recognize the number, so the code is as follows tesseract::TessBaseAPI tess; if (tess.Init("e:\\resources\\tesseract\\tessdata","eng",tesseract:: OEM_LSTM_ONLY)) { cerr <<