SQL Server 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. SQL Server

--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @sTmp1 nvarchar(4000)
    DECLARE @success int
    SELECT @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

    DECLARE @pdf int
    EXEC @hr = sp_OACreate 'Chilkat.Pdf', @pdf OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/scanned_with_ocr.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        RETURN
      END

    DECLARE @json int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @json OUT

    DECLARE @jsonOut int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @jsonOut OUT

    --  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.
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END


    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[0].textSource'
    PRINT 'textSource: ' + @sTmp0

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[0].rating'
    PRINT 'rating: ' + @sTmp0
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  The quality report flags the page, because OCR text is only as good as the OCR was.

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[0].issues[0].code'

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp1 OUT, 'quality.pages[0].issues[0].message'
    PRINT 'issue: ' + @sTmp0 + ' - ' + @sTmp1

    --  "exclude" ignores invisible text altogether: the page then has no text at all.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'invisibleText', 'exclude'
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[0].textSource'

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp1 OUT, 'text'

    PRINT 'With invisibleText excluded, textSource: ' + @sTmp0 + ', text: [' + @sTmp1 + ']'

    --  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: []

    EXEC @hr = sp_OADestroy @pdf
    EXEC @hr = sp_OADestroy @json
    EXEC @hr = sp_OADestroy @jsonOut


END
GO