Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.abbyy.com/llms.txt

Use this file to discover all available pages before exploring further.

To create an OCR skill, follow these steps:
1

Create a new OCR skill

In the Skill Catalog, click the Create button in the toolbar.
2

Select the OCR skill type

Select the OCR Skill skill type. The Create OCR Skill dialog box opens.
3

Configure General settings

On the General tab:
  • Enter a name and description for the new skill.
  • Select the Technology Core version. We recommend selecting the latest version.
Image ProcessingUnder Image Processing, open the PDF Processing Mode dropdown and select the processing mode for PDF documents:
  • Default (Recommended) — Uses the embedded PDF text layer when available and supplements with OCR as needed. This is the default setting.
  • Use Text Layer Only — Extracts text from the embedded PDF text layer. If no text layer exists, Vantage falls back to OCR automatically.
  • Use OCR Only — Ignores any embedded PDF text layer and performs full OCR on the document.
For more information about each mode and guidance on which to choose, see PDF Processing Mode.
4

Select recognition languages

On the Languages tab:
  • In the Allowed Languages section, select one or several document recognition languages. During processing, the document language will be automatically chosen from the languages specified during setup. Note that the number of selected languages may affect recognition speed and quality.
  • If the document contains handwritten text, enable the Handwritten option in the Text Appearance section.
5

Configure image enhancements

On the Image Enhancements tab, Crop Image and Correct Page Orientation are enabled by default. Optionally, turn off these features if your documents do not require them.
  • Crop Image crops the image to the edges of the original document.
  • Correct Page Orientation automatically rotates the image to restore its original orientation.
6

Enable barcode recognition

On the Barcodes tab, enable the barcode types that may appear on your documents. The number of selected barcode types can affect recognition speed. If you don’t need to recognize any barcodes, click the button with the number of selected options in the header of the Barcode Types table and click Deselect all.
If you are processing several document files using an OCR skill as part of a single transaction, all files will be merged into one. As a result, the number of output files will be identical to the specified number of export formats.
7

Choose export formats

On the Export tab, select one or several document export formats.

​
Available export formats

  • JSON (default format):
    • Text only (default option). The exported JSON file will only contain recognized text without preserving the document layout. If you select Text only, you cannot export to DOCX, XLSX, and PPTX.
    • Preserve document structure. The exported JSON file will contain recognized text and the document layout will be preserved as well.
  • XML:
    • Text only. The exported XML file will only contain recognized text. The document layout will not be preserved. If you select Text only, you cannot export to DOCX, XLSX, and PPTX.
    • Preserve document structure. The exported XML file will contain recognized text and the document layout will be preserved.
  • ALTOXML:
    • Text only. The exported ALTO XML file will only contain recognized text; the document layout will not be preserved. If you select Text only, you cannot export to DOCX, XLSX, and PPTX.
    • Preserve document structure. The exported ALTO XML file will contain recognized text and the document layout will be preserved.
Export options (Text only and Preserve document structure) for JSON, XML, and ALTOXML cannot be different. If you specify another export option for one of these formats, this option will be applied for the other formats.
  • PDF:
    • PDF/A-3a (the default PDF export format)
    • PDF/A-3b
    • Image-only. Non-editable PDF in PDF/A-3b standard
For each PDF export option, choose between “smaller file size” (default option) and “maximum quality”. Smaller file size is achieved by using Mixed Raster Content (MRC) compression, which determines optimal compression rates separately for the text, the pictures, and the background.
  • TXT
  • DOCX (Microsoft Word):
    • Editable. The exported DOCX file preserves the original format and text flow but at the same time allows for easy editing. The output document may differ from the original image.
    • Exact. The exported DOCX file maintains the formatting of the original document. This may limit the changes that can be made to the text and formatting of the output document.
  • XLSX (Microsoft Excel)
  • TIFF
  • JPEG:
    • Maximum quality. The exported file contains a JPEG with a compression level of 95%.
    • Reduced size. The exported file contains a JPEG with a compression level of 75%.
  • PPTX (Microsoft PowerPoint)
  • HTML

OCR skill

Overview of the OCR skill and what it can extract.

PDF Processing Mode

Control whether Vantage uses the embedded PDF text layer, OCR, or a combination.

OCR activity

Run an OCR skill as part of a Process skill workflow.

Data export formats

Reference for every export format and option.

Technology Core versions

Choose the engine version that powers a skill.