Using the IRIS OCR engine on Server/Desktop

In addition to the default Tesseract 4 based OCR module, Apryse offers the IRIS OCR Module based on the IRIS iDRS engine. This package is licensed separately from the default OCR module and may provide better results in some cases, especially when considering multiple disconnected text snippets on a page, as might occur in documents such as magazine covers or a CAD documents. The IRIS module is currently available on Windows and Linux Platforms.

The IRIS OCR module requires no special installation step, beyond downloading the appropriate package, and extracting it overtop of a previously expanded Apryse SDK package.

Generally speaking, the IRIS module behaves the same as the default OCR module. In particular, any of the operations using the OCRModule class described within the OCR workflow page will work without any modification. The one exception to this is the case where there are multiple OCR modules present and accessible by the SDK. In this case the IRIS module must be selected by setting the OCREngine option on the OCROptions object: OCROptions.setEngine("iris")