13.2.2 OCR cluster (Host1, Host2, ...)
Text recognition (OCR) normally runs directly on the ArchivistaBox. Text recognition takes plus/minus a few seconds per page. If a large number of documents or pages are captured, there can be considerable delays in text recognition. To avoid this, the text recognition can be divided over several ArchivistaBoxes. The text recognition can be divided into up to several hundred or thousand processes in order to obtain the results in real time.
This option must be enabled for licensing purposes. Of course, the appropriate hardware is also required.
2024-02-28 (c) by Archivista GmbH, CH-8118 Pfaffhausen