When processing invoices for AP automation, header extraction is the process of using Optical Character Recognition (OCR) to extract the key data in the top area, or header, of the invoice. Usually, the OCR is combined with a pattern matching, or key-value, extraction method that finds specific terms and extracts the information that follows. Below is typical information deemed the header:
- Invoice Number
- Invoice Date
- Vendor Name
- PO Number
This identifying information is used as critical information when integrating with an ERP or Accounting System. The other type of extraction when it comes to invoice processing is line item extraction. The chief goal of automated extraction is to reduce manual keying of information through automation and validation. This adds to efficiency and reduced costs.