Ocr with the Tesseract Interface

OCR with the Tesseract interface

The source code seemed to be geared for an executable, you might need to rewire stuffs a bit so it would build as a DLL instead. I don't have much experience with Visual C++ but I think it shouldn't be too hard with some research. My guess is that someone might have had made a library version already, you should try Google.

Once you have tesseract-ocr code in a DLL file, you can then import the file into your C# project via Visual Studio and have it create wrapper classes and do all the marshaling stuffs for you. If you can't import then DllImport will let you call the functions in the DLL from C# code.

Then you can take a look at the original executable to find clues on what functions to call to properly OCR a tiff image.

Tesseract OCR gives really bad output even with typed text

I've found a decent workaround. First off I've made the image larger. More area for tesseract to work with helped it a lot. Second, to get rid of non-digit outputs, I've used the following config on the image to string function:

config = "--psm 7 outputbase digits"

That line now looks like this:

speed = pytesseract.image_to_string(im_c, config = "--psm 7 outputbase digits")

The data coming back is far from perfect but the success rate is high enough that I should be able to clean up the garbage data and interpolate where tesseract returns no digits.



Related Topics



Leave a reply



Submit