We investigated an algorithm that could be used for the splitting and reordering of pages in digital dossiers in the banking sector. Within the industry, large amounts of documents need to be analyzed and processed, for example in the application process of a mortgage or consumer credit. Quite often, multiple documents are delivered within one pdf file and should be separated for further analyses. The knowledge gained from this research aligns well with our DocStreet solution and ensures that an appropriate way of automatically ordering files has been found. The application can also be used for other purposes, such as the digitization of archives.
For the entire paper, please go to: http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=LNl5K7Z4Jww=&t=1
A whitepaper about the same subject is available here.
Questions? Contact Wessel Stoop: firstname.lastname@example.org