You are here: Home Products DocXP® How DocXP® Works

How DocXP® Works

In only 4 steps DocXP® provides a means of capturing document images, verifying and exporting data, and filing or archiving the images and data in a way that allows them to be retrieved quickly and efficiently.

Step 1. Scanning

Working with any ISIS or TWAIN scanner, DocXP® allows the user to scan directly from the application and display each and every image on-screen during capture. This enables the user to ensure that the quality of the images are at the highest possible level. Good quality images will reduce the workload of the operator in subsequent data capture processes as more data will be read correctly.

Images are displayed page by page as the scanner scans the images one by one. Pages can be rotated and pages can be moved before and after other pages. Once the scanner operator has completed the operations on the document, it can be saved and will be made into a DocXP® document. Forms that have been configured for capture by DocXP® will be automatically rotated by the application.

Step 2. Processing documents

DocXP® provides fully automated classification of structured and unstructured documents.

DocXP® processes structured forms without user intervention. It automatically recognises scanned pages, and reads hand printed, machine printed and check box information to a high level of accuracy. It includes powerful page level pre-processing as required, cleaning up the image and scaling the page to the right size for interpretation.

When DocXP® extracts information from an unstructured document, such as an invoice, it automatically indicates to the system what is to be captured and from where on the page. It has an extremely intuitive interface and intelligently captures all the relevant data at the time of scanning.

DocXP® when processing unstructured documents:

  • finds and reads summary data from forms it has not previously seen
  • captures individual line data, for example, an individual item quantity, item descriptions, product codes and amounts.

Step 3. Validation & correcting documents

Once the document has been processed and the data extracted, the character Inspection module ensures that the captured data is free of errors. Character Inspection allows the operator to quality check high confidence characters and quickly flag up any incorrect or suspect characters.

Apart from operator validation, the fields on a form can have additional logical validation applied as well as cross validation between fields. This approach ensures captured data exceeds the 99% accuracy that is required.

The Index module allows the user to review the suspect characters identified automatically as well as those previously flagged up by the operator during Character Inspection. DocXP® is very accurate on correctly interpreting most of the characters on the forms so verification is a speedy process. 

Step 4. Filing & retrieval

 DocXP® includes an easy to use archive and retrieval function that enables indexed documents to be stored during processing or when imported from other applications.

The retrieval function enables the operator to enter appropriate search criteria and access all of the matching documents easily. The user can zoom in, rotate, export images and save as a PDF.

The data for all documents is always online and instantly available. Using Windows Explorer 5.5 or above will enable you to run web based retrieval.

DocXP® also offers web based invoice approval which allows you to integrate with a corporate email system to completely automate the invoice approval process. Supplier invoices can be turned around much easier whether they be in paper or email form.