|
|
Wide support for different image types such as TIFF and JPG in addition to PDFs ensures that maximize value is extracted from image based documents. Adlib's OCR software can even be configured to automatically convert any document type that is not already searchable to PDF.
|
|
|
Recognizes 119 Languages using 17 Language Dictionaries to ensure the highest possible accuracy.
|
|
|
The OCR process can be optimized for speed or accuracy to support the requirements for all document workflows.
|
|
|
Zonal OCR enables the extraction of data from documents that can be used for analysis or to drive business logic.
|
|
|
De-skew and De-speckle are settings that can be used to optimize the accuracy of the OCR process. De-skew automatically straightens the document while de-speckle removes black dots from the original scanned image.
|
|
|
Documents that exceed a time or error threshold can be identified and optionally routed to an error folder.
|
|
|
The barcode recognition option augments the out-of-the-box functionality with support for both 1D and 2D barcodes.
|
|
|
The Optical Mark Recognition (OMR) option adds support for recognizing optical marks (check boxes) on forms and turn them into meaningful data.
|
|
|
Adlib's OCR software can be configured to output recognized text in both XML and CSV formats.
|