Turns out I need to properly crop the image so only the number that's appear. It will not work with those line.
On Monday, February 24, 2020 at 11:19:13 AM UTC+7, ajsaprl wrote: > > Hi, I'm trying to recognize this simple image with tesseract: > [image: converted.jpg] > Image size: 400 × 100 pixels > Image DPI: 300 pixels/inch > > Does anyone knows what makes tesseract throw error like this one? > Failed to load any lstm-specific dictionaries for lang engnumCAPS!! > Tesseract Open Source OCR Engine v4.1.1 with Leptonica > Empty page!! > Empty page!! > > I already resized my image to 300 DPI and I use some traineddata such as > the default eng.traineddata or digits traineddata > <https://github.com/Shreeshrii/tessdata_shreetest/blob/master/digits.traineddata> > but > all of them giving the same error. > Can you help me with this one? > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/fb61e5bb-04ea-4c05-8cf5-065f2f2ef16b%40googlegroups.com.
