OverviewDescriptionBenefitsFeaturesScreenshots 

Description

Why Recostar Full Page Reader?

Extracting Text from Images

Initially, scanned documents and faxes are merely an accumulation of pixels often with cryptic file names – information that is that is hard to work with for the user. In order to search for specific documents and information contained in them, it is necessary to identify the text using OCR. And that is exactly what RecoStar Full Page Reader does.

RecoStar Full Page Reader is used in all areas pertaining to the generation of large documents volumes, e.g. the scanning and the storing of documents in archives or document management systems. The data generated by the software is either stored as an index to the document or directly integrated into a document, e.g. a PDF-file.

In order realize advanced document classification and document analysis for applications like automated mailroom or processing of incoming invoices one needs access not only to the text itself but also to the geometric data of the individual characters, their plausibility and possible alternatives. An optional extension to RecoStar Full Page Reader includes this information.

How does RecoStar Full Page Reader work?

Depending on the settings, the software converts scanned documents into a searchable-PDF or pure text (XML format, ASCII text). It allows processing of all major bitmap formats: FAX, TIFF, JPG, BMP, GIF and PDF.

Every page of a document is analyzed with regard to its content, i.e. the software identifies which parts of the document contain text, images or graphics. The software then divides the text passages into paragraphs, lines, words and characters, converts them using the integrated OCR function checking and correcting them by means of various semantic techniques. The text content of the document is then ready for further processing.