tesseract
tesseract copied to clipboard
Tesseract 4.1.0-beta1 initialiazation error 1 error
Tesseract 4.1.0-beta1
All trained data for 4.0 dont work except 3.04.00. Unfortunately, the accuracy and confidence of 3.04.00 is very bad. Where can i find an accurate trained data for this version?
"type": "https://tools.ietf.org/html/rfc7231#section-6.6.1",
"title": "Failed to initialise tesseract engine.. See https://github.com/charlesw/tesseract/wiki/Error-1 for details.",
"status": 500,
"detail": " at Tesseract.TesseractEngine.Initialise(String datapath, String language, EngineMode engineMode, IEnumerable1 configFiles, IDictionary2 initialValues, Boolean setOnlyNonDebugVariables) at Tesseract.TesseractEngine..ctor(String datapath, String language, EngineMode engineMode, IEnumerable1 configFiles, IDictionary2 initialOptions, Boolean setOnlyNonDebugVariables) at Tesseract.TesseractEngine..ctor(String datapath, String language, EngineMode engineMode)
From the tessdata repo: https://github.com/tesseract-ocr/tessdata/tree/4.0.0
On Thu, 25 Jun 2020, 21:09 Async Technology, [email protected] wrote:
All trained data for 4.0 dont work except 3.04.00. Unfortunately, the accuracy and confidence of 3.04.00 is very bad. Where can i find an accurate trained data for this version?
"type": "https://tools.ietf.org/html/rfc7231#section-6.6.1", "title": "Failed to initialise tesseract engine.. See https://github.com/charlesw/tesseract/wiki/Error-1 for details.", "status": 500, "detail": " at Tesseract.TesseractEngine.Initialise(String datapath, String language, EngineMode engineMode, IEnumerable1 configFiles, IDictionary2 initialValues, Boolean setOnlyNonDebugVariables) at Tesseract.TesseractEngine..ctor(String datapath, String language, EngineMode engineMode, IEnumerable1 configFiles, IDictionary2 initialOptions, Boolean setOnlyNonDebugVariables) at Tesseract.TesseractEngine..ctor(String datapath, String language, EngineMode engineMode)
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/charlesw/tesseract/issues/519, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAB7HSAK3ACUAOVZLXYWZX3RYMV5JANCNFSM4OIIILOQ .
First I set properties to ‘Copy Always’. It didn’t work. I was able to get this working by restarting visual studio. Thanks.
I noticed all the trained models do not recognize MRZ characters on passports or IDs. Characters such as <<<<<<< is either represented by kkkkkkkk or LLLLLLLLL. Sometimes CCCCCCC.
Is there a way to add more training to the model or get a better trained model. My primary use case of tesseract is for passports and identity cards containing MRZ.