Generates searchable PDF and PDF/A documents.
AutoOCR is an OCR processor  watching pre-defined folders, converting automatically new added or changed image documents to fulltext searchable PDF or PDF/A documents.

AutoOCR works as Service!

Can be defined during Setup if the AutoOCR will run as standard application or as a service. If defined as service the applications allows the configuration as well as start/stop of the service. Once started the UI can be closed and OCR will work in background.

Single-page processing of multi-page documents:
Split before OCR processing of multipage documents to single page TIFF and PDF. When processing very large documents with hundreds or thousands of pages the OCR engine normally loads all pages into memory and then starts the processing. For this reason, a function was implemented which enables OCR processing on the basis of performing individual pages. If an error occurs on a single page not the whole document will be rejected as faulty.

Replacing OCR Error pages by PDF Image pages:
If an error in the single-page OCR processing occurs, so a single page will be replaced by a directly converted PDF image page.

Image2PDF processing as a processing option for folders:
The functions of our Image to PDF (/ A) have been integrated to the AutoOCR software.

AutoOCR as Alfresco Transformer

The OCR function will be an action directly at the folder. If there will be put a scanned document to the Alfresco Folder the process will start automatically and the document will be handled to the AutoOCR service. The result is an searchable PDF file which can be found immedeately after that with the Alfresco full text index.

Supports Abbyy FineReader Engine Version 9.x and 10.x

With its modular and flexible concept AutoOCR not only can be used with just one OCR Engine, but also is able to integrate many different OCR engines and use them parllel. AutoOCR can be adapted easy to new OCR developments and products and the user is enabled to arrange the solution based on his requirements.

At the moment we support 2 OCR Engines - iOCR - because unlimited and fast, as well as ABBYY FineReader - because this represents the curently best solution on the entire market. More Engines can be added and integrated via a standardized Interface - „Generic OCR" and we consider future developments without changing the basis product.