# What Computer Vision Does — Computer Vision

Source: https://www.skillbyai.com/en/computer-vision/i-tasks

> The main tasks and where they are used.

## Classify, detect, segment, track, measure

**Computer vision** extracts information from images and video. Core tasks: **classification** (what is in this image?), **object detection** (what objects, and where, as boxes), **segmentation** (which pixels belong to which object or class), **keypoint and pose estimation**, **tracking** across video frames, **optical character recognition**, and **3D reconstruction** and measurement. Applications range from medical imaging and manufacturing inspection to retail, agriculture, document processing and driver assistance. Classical image processing and modern deep learning both play a role.

## From light to numbers

Computer vision turns grids of pixel values into useful decisions.

![Three ideas: tasks, pixels, colour spaces.](assets/figures/computer-vision/section-1-map.svg) — Figure 1.1 — Tasks, pixels and colour spaces.

## Tasks and their outputs

Choose the task from the output you need.

```text
task                    output                              example use
classification          label (+ probability)               is this X-ray normal?
object detection        boxes + labels + scores             count people in a store
semantic segmentation   class per pixel                     road vs sidewalk
instance segmentation   mask per object                     separate touching cells
keypoints / pose        point coordinates                   exercise form feedback
OCR                     text + positions                    read invoices
tracking                object identities over time         traffic flow analysis
```

## Pick the cheapest sufficient output

If you only need to know whether a defect exists, classification is cheaper to label and run than segmentation.

**Quiz:** Which task outputs bounding boxes with labels?

- [ ] Semantic segmentation
- [ ] Image classification
- [x] Object detection
- [ ] OCR only

*Answer:* Object detection. Detection localises objects with boxes.