Intermediate · Computer Vision

Image Segmentation

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

TL;DR. Classifying every pixel in an image to delineate objects and boundaries with detailed spatial understanding.

Technical Definition

Classifying every pixel in an image to delineate objects and boundaries with detailed spatial understanding.

How it works

Image segmentation assigns a class label to every pixel. Semantic segmentation labels categories, instance segmentation distinguishes individual objects, panoptic combines both. U-Net is classic for medical imaging. SAM by Meta achieves zero-shot segmentation.

Visual Explanation (flowchart)

Input Image → Encoder (downsampling) → Bottleneck → Decoder (upsampling + skip connections) → Per-pixel Class Map

Related Concepts

• Convolutional Neural Network (CNN) — A neural network that uses learnable filters to detect spatial patterns like edges, textures, and objects in images.
• Deep Learning — A subset of machine learning using neural networks with many layers to learn hierarchical representations from large datasets.
• Object Detection — A computer vision task that identifies and localizes multiple objects in an image with bounding boxes.