[tesseract-ocr] Re: Language file for MICR font

Hi Anurag, Can you tell us what you did to solve the *other_case < unicharset_size:Error:Assert failed:in file unicharset.cpp, line 737 error?* Am getting this error whenever I try adding a new .traineddata file! On Thursday, October 30, 2014 at 8:52:13 AM UTC-4, Andrew Litvinov wrote: > > F

[tesseract-ocr] Path for output file

Hello, the command tesseract "D:\Palmenwald\Palmenwald-J_0001.jpg" "D:\Palmenwald\test" -l deu-frak does not work. I get an error "cannot create output file" The same Command without specified path for the output file (tesseract "D:\Palmenwald\Palmenwald-J_0001.jpg" "test" -l deu-frak) create

Re: [tesseract-ocr] Unable to locate dictionary files

Thanks a ton! On Monday, 2 February 2015 21:53:12 UTC+5:30, shree wrote: > > > https://code.google.com/p/tesseract-ocr/source/browse/?repo=langdata#git%2Feng > > https://code.google.com/p/tesseract-ocr/source/browse?repo=tessdata#git > > > http://tesseract-ocr.googlecode.com/svn-history/trunk/doc/

[tesseract-ocr] Preprocessing advice for digits on colored background

Sorry if this has been asked before... newbie... I looked at some similar questions but nothing quite matched my scenario, although it must be common: I need to OCR photos of labels that contain white digits on a background of one of 5 background tints, in a tiled format. Please see this example

[tesseract-ocr] skew correction of a single character

HI Is there a way to detect and correct the skew of a single character by using OSD or any other means?.I want to detect "A" but the skewed "A" is giving "B" when passed to tesseract. -- You

Re: [tesseract-ocr] Unable to locate dictionary files

https://code.google.com/p/tesseract-ocr/source/browse/?repo=langdata#git%2Feng https://code.google.com/p/tesseract-ocr/source/browse?repo=tessdata#git http://tesseract-ocr.googlecode.com/svn-history/trunk/doc/combine_tessdata.1.html pecify option -u to unpack all the components to the specified

[tesseract-ocr] Unable to locate dictionary files

Hello, I have installed tesseract manually and also downloaded english training data and put it in the corresponding directory. But I am unable to locate several dictionary files like freq_dawg, and other similar files. Where are they located? Also, Which c++ files in the source co

[tesseract-ocr] Neural nets in tesseract?

Hello, Does tesseract OCR use any neural nets? If so, could someone provide me more information about the kind of neural nets it uses. I saw that the cube uses CNN's but I couldn't find any information regarding the type of neural nets for tesseract. Thanks. -- You received this

[tesseract-ocr] Configure the minimum width of characters

Hello everybody, Is it possible to tell tesseract the minimum width of a character? It seems results are wrong with some maybe difficult characters for Arabic texts. Best regards, -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscrib