I tried using the Python OCR SDK with a PNG image file like below:

 

$ python3 process.py capture.png result.txt

 

and it worked, normal text was found in result.txt

 

however, when using a static PDF file, the OCR SDK returns unreadable binary into the result.txt file. I used this command string:

 

$ python3 process.py -pdf test.pdf result.txt

 

I can't find any help in the documentation so I'm guessing I'm using the tool wrong here. I will attach the result.txt from the PDF command.