To sustain the availability of today's fast growing collections it is becoming more and more necessary for cultural heritage institutions, libraries and private collectors to ensure electronic access to the single book, newspaper or magazine through digitization. Our technology helps to convert huge amounts of pages in short time periods and to keep large scale digitization projects with millions of pages concise, by using a high level of automation.

docWORKS digitally disassembles electronic, paper, microfilm, or microfiche documents to its constituent parts and creates searchable content while

• preserving the original look and feel
• tagging structural and semantic metadata
• producing content for digital asset management systems
• creating access to all documents through a browser

Features

• double page splitting
• image pre-processing
• layout analysis
• full text OCR
• ISR structure recognition
• metadata creation for research and long term preservation
• quality control with automated reject conditions
• easy interface to digital asset managment systems