Using Sophisticated Data Extraction Technology, IMSCAN's Intelligent Recognition and Classification Module can automatically identify incoming documents from a variety of sources. Documents arriving via fax or in paper format are scanned and read using a combination of OCR and ICR technologies. Incoming emails are already in a text format and so do not require conversion.

The documents are then processed by the IMSCAN Classification Module which analyses the text of each document to identify it's business area and thereby it's recipient destination. The Classification Module then processes each purchase invoice by reading it's content using OCR technology. The information extracted is matched against the knowledge base of suppliers using the fuzzy logic database and the Classification Module confirms the invoice as originating from a known supplier.

Once the invoice has been classified it is then searched for the key financial information which is required by the solution to automate the invoice matching process.

The IMSCAN Classification Module uses a master database of approved suppliers which are extracted from the host system. The Classification Module uses fuzzy database technology to identify the relevant supplier based upon the systems' knowledge of each supplier.

Additional analysis is performed on the extracted data to provide useful index and metadata details for the business processes that follow. Key index fields aare extracted by searching in a pre-configured area of each document where the fields are expected to be found.

Data Line Items can be extracted and verified using the line item extraction module available within the IMSCAN Classification system. This module enables the line item entries within an invoice to be extracted and made available to other systems and applications, such as accounts software and spreadsheets.