My input also has param (to indicate ID card/passport). I just need to improve my result. (Language in IDCard, passport is vie. The existed vie.trainedata dose not contain some fonts (ex: OcrB)
Vào 16:02:15 UTC+7 Thứ Bảy, ngày 13 tháng 4 năm 2019, Nitesh kc đã viết: > > *How are you planning to classify contents from (ID,passport)???* > > On Friday, March 29, 2019 at 3:26:55 PM UTC+5:45, Trong wrote: >> >> Hi friends, >>> I'm using Tesseract 4.0 to ocr some limit form (ID card, passport). >>> Currenly the result is 80% correct and I need to improve. (there are >>> constan words in images but it didn't be corrected ex: Name, Date Of >>> Birth..) >>> (It take a lot of my time to try on windows, before I knewn Tess 4 >>> trainning tool dose not support windows :( ) >>> I visited >>> https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00 >>> to known how to train tesseract but i did not successfully. >>> If you have a same problem, please help me by sharing the most simple >>> way to train tesseract 4. >>> Env: Ubuntu 18, Tesseract 4.0 >> >> >> Thank you >> >> -- 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 [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/6e65be4e-be9f-4fd6-bc9e-1276c68b16a9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
