Microsoft Form Recognizer is an optical character recognition (OCR) tool that can be used to retrieve information from scanned documents such as AP invoices, and populate the corresponding Coins ERP+ records.
Running
Setup
Rules
Running Microsoft Form Recognizer
You can run Microsoft Form Recognizer:
Automatically from the Import Scanned Images function. This populates the batch directly.
From the OCR Workbench. This lets you check the values before creating the batch.
For Accounts Payable invoices, using the Auto Index button in Document Capture Workbench.
Setup
Licensing
Microsoft charge per page sent to the API. The X-MSFR license lets you set a monthly number of pages. Users receive an email if they reach the limit and will be unable to use the service if they reach twice the limit for the month. The MS Service Usage Inquiry shows the current position and lets a super-user account override the limit for a month.
Connecting to the Service
The form recognizer requires a suitable resource to be set up in Azure (not covered here).
The following DM parameters need to be set:
DM/MSFREP
Microsoft Form Recognizer endpoint
The endpoint for the Microsoft Forms Recognizer.
DM/MSFRSUB
Microsoft Form Recognizer subscription
The subscription key for Microsoft Forms Recognizer.
DM/OCRENGINE
This needs to be set to MSFR.
Identify which OCR engine to use
The OCR engine to use; for example: MSFR.
OCR Aliases
Aliases are text strings that the OCR process looks for to identify data on the document. These can be used to identify:
Charges (on US invoices)
Tax Registration Numbers
Order numbers
Rules
Scanned images must meet the following criteria:
Format must be JPG, PNG, PDF (text or scanned), or TIFF. Text-embedded PDFs are best because there's no possibility of error in character extraction and location.
File size must be less than 50 MB.
Image dimensions must be between 50 x 50 pixels and 10000 x 10000 pixels.
PDF dimensions must be at most 17 x 17 inches, corresponding to Legal or A3 paper sizes and smaller.
For PDF and TIFF, only the first 200 pages are processed (with a free tier subscription, only the first two pages are processed).
If your PDFs are password-locked, you must remove the lock before submitting them.
If scanned from paper documents, forms should be high-quality scans.