Optical character recognition

Create searchable documents

In addition to splitting and converting the documents, BarcodeOCR is also capable of recognizing the text and make the documents searchable by using an accurate and fast text recognition engine.

Without text recognition (OCR) the texts in your scanned documents are only images of the text which can’t be marked or searched. Searching for a keyword, an invoice number or a specific word won’t return any results.

By converting the documents into searchable documents, BarcodeOCR makes sure that all words are recognized and embedded into the resulting file. If you search for a keyword, the PDF-Viewer will jump to the position the keyword was found.

Combining the text recognition with Windows Explorer, Spotlight on the Mac or any other index engine will allow you to search for your keyword in multiple files at the same time. Identify the file that contains the invoice number can be done within seconds.

In addition, the text recognition you can further enhance or alter the documents:

Automatic alignment of the pages

Pages will be rotated into the natural reading direction: Manually rotating the pages by 90° or 180° is not needed anymore.

Converting documents into Black/White

For the smaller archiving size, the files can be converted into black/white documents and compressed using the CCITT Group 4 algorithm. This way, most files can be significantly decreased.

Changing the density of the document

Documents can be converted into smaller DPI-Resolutions so that they can be archived in a smaller size. If you are forced to scan in a higher DPI size for a better recognition rate (that might be up to the used barcode type and the placement of the barcode) this option makes sure that the file will be shrunk after processing.