Current

Intermediate

First Principles of Computer Vision

Coursera · Columbia University · Updated March 2026

Platform rating

4.5/5

Champ rating

8.3/10

Duration

3-6 months

Classes

150

Learn computer vision from first principles: image formation, 3D vision, segmentation, and recognition from Columbia University.

What you'll get

Work with 3D vision and depth estimation

Understand image formation and optics fundamentals

Implement segmentation and recognition systems

Course Curriculum

12 chapters

Fit

Best for

ML Engineers

Data Scientists

AI Researchers

Deep Learning Practitioners

Not ideal for

Learners seeking only entry-level overviews

Prerequisites & pricing

Prerequisites

Linear algebra, basic programming

Pricing

Subscription

Certification

Certificate

Computer Vision

3D Vision

Image Processing

Segmentation

ShareCompare

Add to StackGo to Course

Alternatives to First Principles of Computer Vision

Compare

Current

Real-Time Video AI on NVIDIA GPUs

NVIDIA Deep Learning Institute (DLI) · NVIDIA

4.6

8.6/10

8 hours self-paced

Build real-time video AI pipelines using NVIDIA DeepStream and TensorRT. Process multiple video streams with GPU-accelerated inference.

$90

ViewAddCompare

In this hands-on class project, you will learn to use Python and OpenCV to extract individual frames from a video file. This project will introduce you to basic ...

In this class, you will create a simple document scanner using the OpenCV library and Python. This can be useful, for example, for scanning pages in a book.

In this hands-on project-based course, you'll learn how to build a real-time multi-face recognizer using Python, OpenCV, and the face_recognition library.