Tcl Requires Chilkat v11.7.0+

Extract the OCR Text Layer of a Scanned PDF

See more PDF Text Extraction Examples

Demonstrates a scanned page that carries an invisible OCR text layer over the page image. The quality report identifies the page's textSource as "ocrLayer". The "invisibleText" filter is "auto" by default, which uses the invisible text only on pages that have no visible text; "exclude" ignores it. Tcl

load ./chilkat.dll

set success 0

#  This example requires the Chilkat API to have been previously unlocked.
#  See Global Unlock Sample for sample code.

#  The PDF used in this example (a page image with an invisible text layer, as an OCR program produces) is available at scanned_with_ocr.pdf

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/scanned_with_ocr.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The page is a picture of a handwritten log with the OCR'd words drawn invisibly over it.
#  "auto" (the default) includes invisible text exactly in this case: on a page with no visible text.
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "textSource: [CkJsonObject_stringOf $jsonOut {quality.pages[0].textSource}]"
puts "rating: [CkJsonObject_stringOf $jsonOut {quality.pages[0].rating}]"
puts [CkJsonObject_stringOf $jsonOut text]

#  The quality report flags the page, because OCR text is only as good as the OCR was.
puts "issue: [CkJsonObject_stringOf $jsonOut {quality.pages[0].issues[0].code}] - [CkJsonObject_stringOf $jsonOut {quality.pages[0].issues[0].message}]"

#  "exclude" ignores invisible text altogether: the page then has no text at all.
CkJsonObject_UpdateString $json "invisibleText" "exclude"
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "With invisibleText excluded, textSource: [CkJsonObject_stringOf $jsonOut {quality.pages[0].textSource}]{, text: [}[CkJsonObject_stringOf $jsonOut text]]"

#  Sample output:

#  textSource: ocrLayer
#  rating: good
#  Keeper's Log, 12 October 1902
#  
#  Wind north-west, fresh. Lamp lit at 5.40 p.m. and burning well all night.
#  
#  Schooner Mary Ann passed inbound at 9 p.m. showing proper lights.
#  
#  Oil on hand: forty-one gallons. Cleaned the lens at dawn.
#  issue: ocrLayer - The text is an invisible OCR layer over an image
#  With invisibleText excluded, textSource: ocrLayer, text: []

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut