Image classification is teaching a model to look at a picture and say which category it belongs to, such as cat or dog.
In plain words
The model is trained on many labelled pictures. Given a new image, it returns a label along with a score for how confident it is. It answers only what is in the picture as a whole, not where each object sits; locating objects is a separate job, handled by object detection models.
A quick example
Give a trained model a photo of a cat. It might answer 'tabby cat' with a high score and list a few similar cat labels with lower scores. A tutorial model can learn to sort photos of flowers by species.
Where you'll meet it
- Sorting and tagging photo libraries.
- Adding keywords to stock photos.
- On-device apps that recognise what the camera sees.
Related
Sources
- DocsImage Classification, Hugging Face Tasks · read 29 Sept 2026
- DocsImage classification, TensorFlow Core tutorials · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.