[tesseract-ocr] tesseract 4.00.00alpha with psm mode 0

Hi, I'm currently trying to use tesseract in page segmentation mode for orientation and script detection only (-psm 0). Using tesseract 4.00.00alpha, i run this mode on the eurotext.tif example as follow : api/tesseract testing/eurotext.tif eurotext -l eng -psm 0 the file eurotext.osd i

[tesseract-ocr] Do I Need to Train Tesseract with Binarized Images?

Hello there! I intend to train tesseract with some book pages, but I'm not sure if there's any difference between training it with the images and training it with binarized pages. Does anyone know? Thanks in advance. -- You received this message because you are subscribed to the Google Groups

[tesseract-ocr] Keeping Less Number of Minimum Characters

Hi, I'm working with vehicle number plate text extraction. The value of constant variable kMinCharactersToTry declared on line 36 at https://github.com/tesseract-ocr/tesseract/blob/master/ccmain/osdetect.cpp must be less since number plate has very fewer number of characters. Currently, it

[tesseract-ocr] Re: How to download the Tesseract trained data for Digital display numbers ( Seven Segments Data trained data )

Hello, I am basically working in electronics field and new to C#.Currently I am working on one project (Image processing in C#) where i am using C#,where in one of the part i have to detect text or digits of 7 segment display image for that on google i found Tesseract solution. For

[tesseract-ocr] Does anyone has tessdata for base58 or base64?

In my project i want to ocr for base58 string.But the eng tessdata so big,So anyone has tessdata for base58? -- 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

Re: [tesseract-ocr] Having issue with Italic characters

Use Tesseract 4.0.0alpha and --oem 1 for LSTM. It works ok with that. --oem 0 with legacy engine gives / instead of i. you could test to see if a better dpi image(300 dpi) works with the legacy engine. ShreeDevi भजन - कीर्तन - आरती @

[tesseract-ocr] Having issue with Italic characters

Hi, I am using tesseract-ocr-setup-3.05.00dev.exe to do OCR and its working fine for me with default training data files . Only facing issue with Italic character . e.g Italic "l" => "/" Italic "i" =>