4

tesseract OCR have a command line interface, which allow us to recognize text from images with some parameters.

Input argumetns are imagename (path to image) outputbase (name of recognized text) and -psm pagesegmode parameters.

pagesegmode values are:
 0 = Orientation and script detection (OSD) only.
 1 = Automatic page segmentation with OSD.
 2 = Automatic page segmentation, but no OSD, or OCR
 3 = Fully automatic page segmentation, but no OSD. (Default)
 4 = Assume a single column of text of variable sizes.
 5 = Assume a single uniform block of vertically aligned text.
 6 = Assume a single uniform block of text.
 7 = Treat the image as a single text line.
 8 = Treat the image as a single word.
 9 = Treat the image as a single word in a circle.
 10 = Treat the image as a single character.
-l lang and/or -psm pagesegmode must occur before anyconfigfile.

But can it library write positions and sizes of recognized text blocks to the specific file or it is an internal information?

Kurt Pfeifle
  • 86,724
  • 23
  • 248
  • 345
Ivan Kochurkin
  • 4,413
  • 8
  • 45
  • 80
  • https://pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/ – Alex P. Mar 14 '23 at 14:41

1 Answers1

7

Tesseract 3.0x supports a "hocr" command option, which produces a HTML-format output file consisting of recognized words and their coordinates. It does not have size/font info, though.

nguyenq
  • 8,212
  • 1
  • 16
  • 16