Computer vision
Computer vision is a major field of computer science concerned with the automatic processing of images and video to extract and interpret the visual information they contain. Practitioners develop mathematical and software tools for processing visual information.
On this page
Source content checked . English translation published 2026-10-27.
In business automation
Computer vision extracts information from an image or scan. In automation, it is used to read forms, labels, and document photos when no structured file is available, then pass the extracted fields to the next process.
Examples
These examples illustrate a possible workflow. Adapt the connections and rules to your own systems.
Reading a shipping label
A warehouse photographs a package label. A vision model extracts the tracking number and address, and the process updates the order. If confidence is low, the image goes to an employee instead of creating an incomplete address.
Relevant tools
- Amazon Textract
- The service extracts text and structure from scanned documents; fields such as amount and account still require verification.
What to check
- Poor lighting or a new form can reduce accuracy without the process detecting that it is wrong.