Recognition of the document that has incorrect text layer

Symptoms

Resulted file after recognition contains an incorrect text layer.

Cause

In some cases when the original document already has a text layer default OCR mode could work incorrectly and OCR is not started.

Resolution

To enable OCR process for the file that already has a text layer, try the following:

  1. Open PDF file in PDF Editor or OCR Editor.
  2. Go to Tools > Options > OCR.
  3. In the PDF Recognition mode choose Use OCR.
  4. Click OK.
  5. Convert the document to the format you need in PDF Editor.
    Or recognize the document anew in OCR Editor.

Have more questions? Submit a request

Comments

2 comments

  • Avatar

    Ayyan Moyer

    https://drive.google.com/drive/folders/1RHcvC-KUhUPcn7lomjH0PG-TPwWw9QBO — original page, recognition settings and result. Only saving the document with the "Discard hidden layer content, and flatten visible layers" option in the PDF viewer and recognizing the resulting file helped. But the quality of the image in the document has deteriorated, and the size has increased several times.

    0
  • Avatar

    Victoria Dvornikova

    Hi Ayyan Moyer,

    Please await a reply from our Support team in the support ticket created based on your question.

    0

Please sign in to leave a comment.