Kon-x Wales Ltd

The Future of Document Imaging and Information Management

Document Imaging and Information management has always carried high up front overheads in terms of document preparation, capture and indexing. Technology now makes these bottle necks a thing of the past.

The desire of users to be able to manage their entire information archives no matter what format their legacy data comes in, has never been stronger. Up until now it has only been the large corporates and Government sectors that have been able to afford to implement Document Imaging and Information Management solutions in any real numbers due to the high cost of capturing and indexing the documentation.

The task of bringing together the mixed bag of different information formats that are held by modern companies has always been difficult. Most companies have paper documents, maybe microfilmed archives and of course the many different electronic formats.

Indexing this information will be either by index fields or by the full document content, either method has until now involved a large amount of manual intervention. Data entry for the index fields or OCR clean up for the full content indexing.

Data clean up on OCR'ed text files carries an expensive overhead, at around £2 per page this adds £20,000 to a small document repository of just 10,000 pages. Key Word indexing is also an expensive option as it is estimated to cost between £5 - £25 per document (average of six pages per document) to build an index that needs continuous management if it is to be intelligent enough to find all the relevant information on an ongoing basis.

Intelligent Archiving

Small to medium sized organizations have realized that their company information is as valuable to them as the information held within large multi national organizations. It is also clear to see that the SME's have accepted the value of document imaging for their paper based documents, but they now want to combine all their other information formats together with the paper documents, making them accessible through the desktop from a single searchable source.

Information repositories are not new; every company has them, from filing cabinets to electronic office documents, CAD files to microfilm. Whatever format the information is held in you need a universal indexing structure on the total document contents of all the different document formats, if you are to be able to find ALL the relevant files that have mention of the topics you are searching for.

Adaptive Pattern Recognition is a unique technology that overcomes the inherent shortfalls of OCR errors within OCR'ed text files making it possible to use the raw OCR'ed ASCII files for full content indexing without spending time proof reading and correcting the errors.

Using APRP (Adaptive Pattern Recognition Processing) we have built a product that will automatically index the entire content of just about any document format. The system is OCR error tolerant and overcomes spelling mistakes within search queries.

PowerRetrieve is a cost-effective document archive system overcoming the need for hours of indexing. Bringing together all document types through a single user interface PowerRetrieve provides the intelligence to search through large information repositories in seconds, finding all documents that contain the relevant information you are looking for, even if the search query is not accurate.

Document Imaging and Information Management, be it locally or over a wide area network, an Intranet or the Internet, now has the technology at a price that makes it available to small and large organizations alike.

Thanks to David Dawes of InfoCAP Technologies Ltd for providing this article. For further reading visit www.infocap.co.uk