COURSE 12Intermediate8 IN-DEPTH LESSONS

Computer Vision

Teaching machines to perceive: object detection, semantic and instance segmentation, optical character recognition (OCR), and vision-language models (VLMs).

Start Lesson 1: Computer vision overview →← All 29 Courses

Course Syllabus & Units

Unit 1

Overview

1 lessons
1.1L1

Computer vision overview

**Computer vision** teaches machines to interpret images and video: what is there, where it is, and sometimes what will happen next.

Read lesson →
Unit 2

Detection

1 lessons
2.1L1

Object detection basics

**Object detection** finds *what* objects are present and *where* (usually bounding boxes). It is more than whole-image classification.

Read lesson →
Unit 3

Segmentation

1 lessons
3.1L1

Segmentation basics

**Segmentation** labels pixels (or regions): what class each part of the image belongs to—finer than a single box.

Read lesson →
Unit 4

Vlm

1 lessons
4.1L1

Vision-language models overview

**Vision-language models (VLMs)** connect images (and sometimes video) with text—captioning, visual Q&A, document screenshots, UI understanding.

Read lesson →
Unit 5

Video

1 lessons
5.1L1

Video understanding overview

Models that interpret video: action recognition, tracking, temporal event detection, video captioning—not only single frames.

Read lesson →
Unit 6

Docs

1 lessons
6.1L1

OCR and documents

**OCR** reads text in images; document AI structures forms, tables, and layouts for downstream RAG or workflows.

Read lesson →
Unit 7

Bias

1 lessons
7.1L1

Dataset bias in vision

How image/video datasets under-represent people, places, and conditions—and how that shows up as unequal error rates.

Read lesson →
Unit 8

Practice

1 lessons
8.1L1

Error analysis for vision

Systematically inspecting vision mistakes by slice: lighting, size, background, demographics, camera type—then fixing data/model/threshold.

Read lesson →