Optical character recognition
Jump to navigation
Jump to search
This article is a stub. You can help the OLPC project by expanding it.
- See Scanning for the OCR of books to create OLPC content.
Optical character recognition (OCR) is the conversion of photographs of text, into editable text.
This page was created mostly in support of Test automation.
Running OCR on an XO
Install gocr.
yum install gocr
Next, get a pnm image of some page of text.
One approach is to take a screenshot.
yum install ImageMagick
Use Record to take a picture of some text, and show it full screen. Then in Terminal,
sleep 5; import -window root pageimage.png
and switch back to Record while the sleep is happening, and wait for the screenshot to be taken.
Convert the image to text.
gocr pageimage.pnm
Resources
- http://gentoo-wiki.com/HOWTO_do_OCR
- http://jocr.sourceforge.net/ GOCR
- http://lem.eui.upm.es/ocre.html Capable of user training. What range of languages might it be used with?
- http://www.gnu.org/software/ocrad/ocrad.html Unexamined.
- http://code.google.com/p/tesseract-ocr/