101 reputation
1
bio website pycloud.blogspot.com
location
age
visits member for 3 years
seen Apr 19 at 23:35

A skeptical-inquirer in the lands of atmospheric sciences...


Jun
22
comment How to extract text with OCR from a PDF on Linux?
By the way, I use tesseract for character recognition: replacing cuneiform line with: tesseract "$page" "$base" hocr
Jun
22
comment How to extract text with OCR from a PDF on Linux?
This is one solution. However without seeing the whole context of the text it is hard to make corrections. It would be nicer to see an interface built within the ocrfeeder.
Jun
21
awarded  Supporter
Jun
21
comment How to extract text with OCR from a PDF on Linux?
Any idea to improve this script to add spell-checking stage to correct errors in recognition step?