tesseract
tesseract copied to clipboard
Sometimes failing to detect multiple columns
Environment
v5.0.0 alpha Windows 10-64 bit
Current Behavior:
I have two very similar documents seen here and here:
In the former, Tesseract with psm=1 parses out two columns, in the second, no matter what tesseract will only detect one column and form line blocks that stretch across the page. The exact command I am executing is: tesseract --psm 1 file.png file hocr
Expected Behavior:
I can't understand why the columns are not correctly detected in the second document. Any ideas? These two images are very similar.
Suggested Fix:
?
@kuhanw your issue probably has a higher chance of getting attention if it includes sufficient information and files to reproduce it (e.g., #2155).
Hello, I have the same problem!! did you resolve this one ?