Question
: Can you use OCR to read data from documents if it is not in the same place on every page?
Answer : Traditional Zone OCR applications extract data from fixed regions and work well when scanning the same document over and over again. However, many types of documents have the same data elements in different locations. A typical example is invoices that come from many different vendors.
The software that you need to accomplish this depends on the number and type of data elements that you want to capture. If you have a low-volume application with less than 10 data elements, SimpleIndex offers a simple, affordable method for extracting data elements based on pattern matching algorithms.
For high-volume applications or documents with more complicated elements, like tables, use ABBYY FlexiCapture. FlexiCapture lets you define complex rules-based document templates to locate the data you need and recognize it with the greatest accuracy.
Topics
