# Image Classification

> AI gives a whole photo one label, such as cat or dog.

**Field:** Artificial Intelligence  
**Category:** Robotics & Vision  
**Also known as:** Image Recognition, Image Labeling

## Think of it like

It is like sorting photos into boxes. One box for cats, one for dogs, one for birds.

## Definition

Image classification is when an AI model looks at a whole picture and gives it one label, such as cat or dog. The model gives each label a score for how sure it is, and the top score wins. It says what the picture shows, but not where the thing is. It is the simplest vision task, and the first one deep learning got very good at. It sorts photos, checks parts in factories, and flags skin spots for a doctor.

## Example

A farm uses image classification on photos of apples on a belt. Each apple gets the label good or bruised, and the bruised ones are pushed off the line.

## Why it matters

It is the base of most vision work. If you only need to know what a picture shows, this is the cheapest way.

## Common mistake

Using it when you need to know where things are, or how many. One label for the whole picture cannot tell you that.

## Three principles

- **One label.** For the whole picture.
- **With a score.** How sure it is.
- **What, not where.** No position.

## Related terms

- [Object Detection](https://learn.benibix.com/term/ai/object-detection)
- [Computer Vision](https://learn.benibix.com/term/ai/computer-vision)
- [Classification (Machine Learning)](https://learn.benibix.com/term/ai/classification)
- [Convolutional Neural Network (CNN)](https://learn.benibix.com/term/ai/convolutional-neural-network)
- [Adversarial Example](https://learn.benibix.com/term/ai/adversarial-example)
- [ImageNet](https://learn.benibix.com/term/ai/imagenet)
- [AI in Healthcare](https://learn.benibix.com/term/ai/ai-in-healthcare)

## Told apart from

- [Image Classification vs Object Detection](https://learn.benibix.com/compare/image-classification-vs-object-detection): People often think image classification and object detection do the same job. Classification gives the whole picture one label, such as cat. It does not say where the cat is. Detection finds each thing in the picture and draws a box around it, with a label for each. Use the first to sort pictures, and the second to find, count or follow things in them.

## Taught in

- [AI in Healthcare and Medicine](https://learn.benibix.com/learn/ai-use-case/ai-in-healthcare-and-medicine): AI Assistants and Chatbots, 13/13

![A photo goes into a model, which gives a list of labels with scores: cat 0.94, fox 0.04, dog 0.02.](https://learn.benibix.com/diagrams/rb-image-classification.svg)

---

Source: https://learn.benibix.com/term/ai/image-classification
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
