ocr.rst
changeset 1136 8d9c9a102827
child 1334 9bf0d5a1f0cf
equal deleted inserted replaced
1135:d98ac8df0e85 1136:8d9c9a102827
       
     1 
       
     2 ======
       
     3  OCS.
       
     4 ======
       
     5 
       
     6 gocr.
       
     7 =====
       
     8 
       
     9   $ gocr $IN.pnm >$OUT.txt
       
    10 
       
    11 ocrfeeder.
       
    12 ==========
       
    13 
       
    14 Document layout analysis and optical character recognition system::
       
    15 
       
    16   $ sudo apt-get install ocrfeeder
       
    17 
       
    18 Using::
       
    19 
       
    20   $ ocrfeeder-cli --o $OUTDIR --format HTML --images $IN.pnm
       
    21 
       
    22 tesseract.
       
    23 ==========
       
    24 
       
    25 Installing::
       
    26 
       
    27   $ sudo apt-get install tesseract-ocr
       
    28 
       
    29 Using::
       
    30 
       
    31   $ tesseract $IN.tif $OUT
       
    32   $ cat $OUT.txt
       
    33 
       
    34 ocropus.
       
    35 ========
       
    36 
       
    37   $ ocropus hocr-to-text screen.ppm
       
    38 
       
    39 ocrad
       
    40 =====
       
    41 
       
    42 Optical Character Recognition program::
       
    43 
       
    44   $ sudo apt-get install ocrad
       
    45 
       
    46 Misc.
       
    47 =====
       
    48 
       
    49 unpapper