About
Resources
© All rights reserved
What is OCR?
Optical Character Recognition (OCR) is a technology that enables you to convert different types of documents, such as scanned paper documents, PDF files or images captured by a digital camera into editable and searchable data.
Share:
What is OCR used for?
OCR technology is used to convert different kinds of images containing written text (typed or printed) into machine-readable text data. Instead of retyping a written text manually, you can convert all the required materials into a digital format within several minutes using a scanner (or a digital camera) and Optical Character Recognition software.
When is OCR used in procurement?
In procurement, OCR is mainly used to scan and digitise information from, for example, printed invoices, purchase order confirmations etc. That means it is used to capture documents and incorporate data into the downstream systems.
How does OCR work?
Using OCR software involves three steps:
Step 1: Pre-processing the document image
Step 2: Character Recognition
Step 3: Post-processing the document image
Main disadvantages of OCR
- Expensive
- Low accuracy, mistakes are likely
- Labour-intensive to correct mistakes created by OCR
- Not all documents can be processed
Alternative to OCR: The Netfira Platform
OCR vs. the Netfira Platform
|
|
OCR |
Netfira Platform |
|
Costs |
The software is expensive, special scanning hardware needed, training, materials and staffing costs |
SaaS solution: Minimal investment costs
|
|
Accuracy |
Low accuracy, mistakes are likely
|
Very high data accuracy, hardly any errors through AI
|
|
Correcting errors |
Labour-intensive |
AI is capable of learning and is becoming more and more precise, check and correct discrepancies easily
|
|
Scope of application |
Only works with specific formats |
No restrictions, AI can also work with and structured unstructured data
|