ScreenOCR

#!/bin/bash
# DEPENDENCIES: tesseract-ocr imagemagick scrot yad
# AUTHOR:       Glutanimate 2013 (http://askubuntu.com/users/81372/)
# NAME:         ScreenOCR
# LICENSE:      GNU GPLv3
#
# BASED ON:     OCR script by Salem (http://askubuntu.com/a/280713/81372)

TITLE=ScreenOCR # set yad variables
ICON=gnome-screenshot

# - tesseract won't work if LC_ALL is unset so we set it here
# - you might want to delete or modify this line if you 
#   have a different locale:

export LC_ALL=en_US.UTF-8

# language selection dialog
LANG=$(yad \
    --width 300 --entry --title "$TITLE" \
    --image=$ICON \
    --window-icon=$ICON \
    --button="ok:0" --button="cancel:1" \
    --text "Select language:" \
    --entry-text \
    "eng" "ita" "deu")

# - You can modify the list of available languages by editing the line above
# - Make sure to use the same ISO codes tesseract does (man tesseract for details)
# - Languages will of course only work if you have installed their respective
#   language packs (https://code.google.com/p/tesseract-ocr/downloads/list)

RET=$? # check return status

if [ "$RET" = 252 ] || [ "$RET" = 1 ]  # WM-Close or "cancel"
  then
      exit
fi

echo "Language set to $LANG"

SCR_IMG=$(mktemp) # create tempfile
trap "rm $SCR_IMG*" EXIT # make sure tempfiles get deleted afterwards

scrot -s "$SCR_IMG".png -q 100 #take screenshot of area
mogrify -modulate 100,0 -resize 400% "$SCR_IMG".png # postprocess to prepare for OCR
tesseract -l "$LANG" "$SCR_IMG".png "$SCR_IMG" # OCR in given language
xsel -bi < "$SCR_IMG".txt # pass to clipboard
exit