Can we split images into multipages invoices by FCI project?


We are facing a scenario in which we are getting multiple invoices from two Vendors. Is there any way that ABBYY FlexiCapture 12 can split these pdf documents into separated documents and then recognized them for further processed?


The Invoice document definition cannot be used to assemble documents, it should be applied to the already assembled documents.
There are two main possibilities how to deal with the situation when you cannot rely on the fact "one file - one Invoice":

1) you may create a layout that will be able to assemble the documents (it should contain only the reliable Headers and maybe Footers to be able to assemble the Invoice properly, without extracting any fields).
Then you should set up Advanced workflow with additional Recognition and Script stages as follows:

- Scanning (Import)
- Recognition 1 that uses the layout that assembles the pages into documents
- Script stage that deletes the recognition 1 results, but not the pages' assembling
- Recognition 2 that uses the standard Invoice layout on already assembled documents
- all other required stages

2) you may set up the classifier in the Invoice project that will be trained to look for the first pages and then you may use this information for the assembling, for example as it is described in this article:

Separate documents in a stream of input pages

  1. Create a Document Definition for each type of document.
  2. Create sections for each Document Definition.

The classifier will determine which section each page belongs to and whether or not it is the first page in a document, and then classify it according to this data.

Have more questions? Submit a request



Please sign in to leave a comment.