Analyze

Analyzing your forms is the second step in automating data collection. You need to know what kind of form it is and what is on the form so you can quickly and accurately get it to the right place. No matter what kind of documents you have, Formtran can capture and automatically identify documents and extract the data you need.

Formtran means powerful analytical capability:

How can you get the infrastructure you have to work harder for you? How can you implement automated scanning without turning your people into scanner operators? Formtran’s scanning software can work with any image capture device in any location.

  • Classification of documents by format and source. Read .pdf, .tif or other image formats and identify their origination.
  • Classification of documents by content. Documents can be routed to the correct target business process without the need for pre-sorting, reducing document handling costs.
  • Separation of multi-page documents. Multi-page documents can be scanned without inserting pre-printed separator sheets between them, eliminating printing costs and reducing batch preparation time.
  • Indexing of images. Rich index data can be captured from every document, dramatically reducing the need for costly manual keying and enabling powerful search for the captured information and documents. This can reduce the ongoing cost of running any document management system.
  • Data capture. Read data from unstructured, semi-structured or structured forms. Eliminate data entry and ensure accuracy.

Formtran provides cutting edge software to recognize every type of field on a form. Equally important, Formtran provides the expertise to maximize accuracy and throughput for each field on the form based on specific field context, field relationships and other rules. As a result, you experience more automation and less human intervention.

Unstructured Forms

For forms that contain the same information but in different places, unstructured forms processing does the trick. Unstructured forms processing uses the latest in OCR technology to identify forms, locate fields and read data.

  • Invoices
  • Purchase orders
  • Loan documents
  • Bills of lading
  • Government forms
  • HCFA 1500, UB92 hospital billing forms
  • Utility bills
  • Payment vouchers
  • Insurance claim forms

Unstructured forms technology significantly improves accuracy by providing for additional logic for finding and reading fields. With unstructured forms processing, it’s “what you want to capture, not where you want to capture.”

  • Detect specific data anywhere on a page
  • Automatically find tables including header, footer, rows and columns
  • Find text, dates, dollars and other specific data types
  • Locate fields relative to other fields found on a form