How to specify an extraction area in FineReader Engine 12

Avatar

Sergey Pilipchuk

Question

How to manually specify an area for text extraction in FineReader Engine 12?

Answer

This code-snippet demonstrates how to specify an extraction area:

FREngine.IRegion region = engineLoader.Engine.CreateRegion();
region.AddRect(244, 287, 1422, 356);
document.Pages[0].Layout.Blocks.AddNew(FREngine.BlockTypeEnum.BT_Text, region, 0);
document.Pages[0].Layout.Blocks[0].GetAsTextBlock().RecognizerParams.SetPredefinedTextLanguage("Japanese");
document.Pages[0].Recognize();
document.Synthesize();
string text = document.Pages[0].Layout.Blocks[0].GetAsTextBlock().Text.Paragraphs[0].Text;

Have more questions? Submit a request

Comments

1 comment

Sort by Date Votes
  • Avatar

    Nishar Ahamed

    Hi,

    I am using FREngine 12 and trying to extract text from PDF file

    I have developed the code based on your code snippet

    But unable to get the text 

    Please look in to the below code snippet and provide your suggestion

    ---------------------------------------------------------------------

    document.AddImageFile( pdffilePath, null, null );

    document.Process( null );

    IRegion region = engine.CreateRegion();

    region.AddRect(244, 287, 422, 356);

    IFRPages pages = document.getPages();
    int pagecnt = pages.getCount();
    displayMessage("Pages:"+pagecnt);

    // Get single page in document
    IFRPage page = pages.getElement(0);

    page.Analyze(pageparams,objparams,Recogparams);
    page.Recognize(syn_params,objparams);

    ILayout layout = page.getLayout();
    page.setLayout(layout);

    ILayoutBlocks blocks = layout.getBlocks();
    IBlock block = blocks.AddNew(BlockTypeEnum.BT_Text, region, 0);

    ITextBlock txtblck = block.GetAsTextBlock();
    Recogparams.SetPredefinedTextLanguage("ENGLISH");

    IText txt = txtblck.getText();
    IParagraphs paras = txt.getParagraphs();
    int i = paras.getCount();
    displayMessage( "cnt-"+i );
    IParagraph parag = paras.getElement(0);
    String text = parag.getText();
    displayMessage( "text-"+text );

     

    ---------------------------------------------------------------------------------

    Please find the output below

    0

Please sign in to leave a comment.