[tesseract-ocr] Re: Inaccurate output from Windows Screen Shot PNG OCR

2018-07-15 Thread Testing Windows Screenshots
Had a breakthrough - John's reply: "Gimp is your friend." https://stackoverflow.com/questions/9480013/image-processing-to-improve-tesseract-ocr-accuracy Note: *Gimp* *Scale Image*: Quality: *Interpolation *must be set to *Linea*r. Cubic gave only 60% text. Now results are 95%. bottom row of nu

Re: [tesseract-ocr] "lstmtraining" stopped but not finished?

2018-07-15 Thread Davaadorj.U
No. Not yet. We might should report this as bug. On Sun, Jul 15, 2018, 18:25 Shree Devi Kumar wrote: > Did you figure out what was causing this? > > > On Thu, Jul 12, 2018 at 8:15 AM Dd U wrote: > >> Hello guys please help me. >> >> >> I'm trying to training for improve Japanese language. Then

[tesseract-ocr] Inaccurate output from Windows Screen Shot PNG OCR

2018-07-15 Thread Testing Windows Screenshots
I'm using TessBaseAPI to scan a png of WIndows screenshot, Issue 1) List of numbers are inaccurate 7254134516423432 1324152643132424 324326178176892 text out=> 72541345 16423432 1324152643132424 324326178176892 Tesseract put a space between 5 and 1 2) Missing numbers If there are 2 note

Re: [tesseract-ocr] "lstmtraining" stopped but not finished?

2018-07-15 Thread Shree Devi Kumar
Did you figure out what was causing this? On Thu, Jul 12, 2018 at 8:15 AM Dd U wrote: > Hello guys please help me. > > > I'm trying to training for improve Japanese language. Then I have a > problem now. > > > lstmtraining is stopped but not finished. It does not using CPU anymore > and nothing