Beginner · Computer Vision

Image Classification

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. The task of categorizing images into one of several predefined classes.

Technical Definition

The task of categorizing images into one of several predefined classes.

How it works

Image classification is a fundamental problem in computer vision. Given an input image, the goal is to assign it a specific label from a set of categories (e.g., 'cat', 'dog', 'car'). Convolutional neural networks are the dominant architecture for achieving high accuracy in this task. It forms the basis for many other computer vision applications.

Related Concepts

• Convolutional Neural Network (CNN) — A neural network that uses learnable filters to detect spatial patterns like edges, textures, and objects in images.
• Object Detection — A computer vision task that identifies and localizes multiple objects in an image with bounding boxes.
• Computer vision — Computer vision enables computers to interpret and understand information from digital images and videos, automating tasks typically done by human sight.