Re: [tesseract-ocr] Questions about recognize Chinese characters

2019-04-10 Thread Aaron Shieh
I tried using --oem 1 but the results are really bad, that's why I resorted to legacy mode. Do you have any luck with LSTM models? -- 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

[tesseract-ocr] Need advice for training_text.txt

2019-04-10 Thread Aaron Shieh
Hi, I noticed in the langdata_lstm/chi_tra repo the training text contains long lines of text, my application requires only identifying single line text with only max of 15 chinese characters, so my question is how should I make my training text? I was thinking something like this, where each

Re: [tesseract-ocr] Need advice for training_text.txt

2019-04-10 Thread Shree Devi Kumar
where each row in the training text is close to what my final application will see: That would be preferable. On Wed, 10 Apr 2019, 21:07 Aaron Shieh, wrote: > Hi, > > I noticed in the langdata_lstm/chi_tra repo the training text contains > long lines of text, my application requires only identi

Re: [tesseract-ocr] confuse whether Otsu Thresholding affects lstm training

2019-04-10 Thread Shree Devi Kumar
Hi Lorenzo, Thanks for detailed description of pre-processing steps. I will link from the wiki so that it is available for easy reference. Thank you for sharing. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and

[tesseract-ocr] Re: Not able to lift text from the attached file please help!!!

2019-04-10 Thread Shobhit Kapil
Hi Shree, Please share your inputs!!! Thanks, Shobhit On Wednesday, April 3, 2019 at 7:58:14 PM UTC+5:30, Shobhit Kapil wrote: > > Hi Team, > > i am using Tesseract version 4 and using page segment mode is LSTM, so > with that i am not able to lift text properly from the attached file, > pleas

[tesseract-ocr] Re: Tesseract on VS

2019-04-10 Thread Shobhit Kapil
Please share any input On Friday, April 5, 2019 at 7:59:26 PM UTC+5:30, Shobhit Kapil wrote: > > Hi All, > > Is there anyone who is using Tesseract on windows using Visual Studio. > > If yes i will be having few questions to ask. > > > Thanks, > Shobhit > -- You received this message because

[tesseract-ocr] Re: Training Tesseract 4 from Scratch

2019-04-10 Thread Shobhit Kapil
Hi Shree, Please share your input for the following questions Thanks, Shobhit On Wednesday, April 3, 2019 at 8:16:36 PM UTC+5:30, Shobhit Kapil wrote: > > Hi Team, > > I am not at all aware of training tesseract 4, is there any way that how > to learn train tesseract 4. > By reading the do