0

As discussed on this SO Question, tesseract often operates better with .png files than with .tiff files. (I have also experienced this directly myself). Unfortunately, there are fewer box editors available that can handle .png files. I therefore am tempted to train my data using .tiff files but then use .png files for my main OCR work. Will doing so reduce the effectiveness of the training? If so, are there any ways to address it (other than just finding a box editor that can accept .png files)?

Community
  • 1
  • 1
Michael Ohlrogge
  • 10,559
  • 5
  • 48
  • 76

1 Answers1

1

Some editors such as jTessBoxEditor (Tesseract AddOns page) support both TIFF and PNG formats. Since TIFF can be multi-page image, it can have a lot more samples for your character set than single-page PNG.

https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract

nguyenq
  • 8,212
  • 1
  • 16
  • 16
  • Interesting, thank you! You know, jTessBoxEditor is what I had been using. I had been trying to use it with a 600dpi .png file (only 212KB) and it simply wouldn't load it. But, when I switched down, even just to 500dpi, it worked. I'm not quite sure what is up with that. But, I had previously just thought that it was impossible to use with .png, based on my experience with the 600dpi file. But, after reading your answer and trying it, it worked! Thanks too for all your great work on the program and your other super helpful answers here on SO. – Michael Ohlrogge Jun 24 '16 at 02:42
  • Also, so that I don't fill up the comments with too many separate questions, I posted [this](http://stackoverflow.com/questions/38018256/tesseract-advantage-to-multi-page-training-file-vs-multiple-separate-files) new question as a follow up to your comment about multi-page `.tif` images. Any insights you have on that would be greatly appreciated too! Thanks! – Michael Ohlrogge Jun 24 '16 at 16:39
  • There should be no limits unless it runs out of memory. Try running the program with a larger JVM heap size and loading your 600dpi image again. – nguyenq Jun 24 '16 at 22:21
  • Ok, thanks. I still did not have success with the 600dpi image. I created a separate question on that [here](http://stackoverflow.com/questions/38026769/jtessboxeditor-cannot-handle-600dpi-png-files) – Michael Ohlrogge Jun 25 '16 at 09:05