Document Recognition

FineReader Sprint uses Optical Character Recognition technologies to convert document images into editable text. Before performing OCR, the program analyzes the structure of the entire document and detects the areas that contain text, barcodes, images, and tables. For more about areas, see Working with Areas.

By default, FineReader Sprint performs document recognition automatically. In this case, the application uses its current settings.

Tip: You can disable automatic analysis and recognition of newly added images in the preferences dialog. For more information, see "Automatic Recognition".

The quality of the retrieved text depends on the correct selection of the document language, original document image, and document structure layout. You can learn how to account for the document's initial characteristics and obtain the best recognition results in How to Improve the Recognition Results.

In some cases, the process can be started manually. If you:

disabled automatic recognition,
changed the original document layout, area, and text properties,
selected the areas on the image manually,
changed the document language.

To do this, click Recognize in the main toolbar.

If you changed the document layout partially, you can start the recognition of one or more selected pages in the document:

For one page, choose Page > Read Page or choose the Read Page command in the shortcut menu of the page.
For multiple pages, select the desired pages, choose Page > Read Page or choose the Read Page command in the shortcut menu of one of the selected pages.

Tip: FineReader Sprint offers a number of features designed for working with multi-page documents. For more information, see "Working with FineReader Documents".