Vision model
Also: vision-language model, image understanding
A model that can look at images as well as read text.
The fuller definition
A vision model processes images; a vision-language model combines visual and language inputs or outputs.
- Image
Chart or page
- Model
Visual representations
- Output
Description or answer
A simplified relationship, not a screenshot or a complete design.
A concrete example
A system describes a chart or answers a question about a page image.
The distinction that matters
Reading an image through a model is not equivalent to exact OCR, especially for small print and precise values.
Related terms
Multimodal
Able to work with more than text, such as images, audio, or video.
Documents & retrievalOCR — Optical character recognition
Turning a picture of text, such as a scanned page, into real text a computer can search.
Reliability & securityHallucination
When the model states something that sounds right but is made up, including cases, quotes, and facts that do not exist.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.