CSE590/MB590 Special Topics
  - Introduction to Computer Vision

The course covers the fundamental concepts in Computer Vision, including probability and mathematical theories, image processing, feature detection, structure from motion, face detection and recognition, etc. The course also introduces the new-generation deep learning tools such as PyTorch and TensorFlow with computer vision applications such as human pose estimate.
  • » 23 hours (8 weeks) in class lecturing plus dedicated mentoring sessions from our faculty of industry experts


  • » 1.5 semester credits for both certificate and master’s degree


  • » Access to high-quality live class recording


  • » Online live classroom available for all classes


  • » Lifetime learning resources for our students


  • $ 990
Unit 1: Course Description

The course covers the fundamental concepts in Computer Vision, including probability and mathematical theories, image processing, feature detection, structure from motion, face detection and recognition, etc. The course also introduces the new-generation deep learning tools such as PyTorch and TensorFlow with computer vision applications such as human pose estimate.

Unit 2: Course Objectives
Learning objectives of this course are:
  • Students will learn the fundamental concepts of computer vision theories and practical solutions
  • Students will learn to use the OpenCV software for solving image processing and computer vision problems
  • Students will learn the PyTorch and TensorFlow tools and workflows for training deep learning network models to solve computer vision problems
Unit 3: Learning Outcomes
After completing this course, students will have the capabilities or skills indicated in the followings:
  • Can describe the main concepts, problem formulation, and known solutions in computer vision
  • Can use OpenCV and Python programming language to solve real world computer vision problems
  • Understand the workflow of PyTorch and Tensorflow and know how to use them to build deep learning network models
Unit 4: Textbook

Computer Vision Algorithms and Applications by Richard Szeliski.

Publisher: Springer-Verlag (2011). ISBN: 978-1848829343

Unit 5: Course Outline (subject to change)
Week Topic
1 Introduction, mathematics, and tools
Camera model and image formation
2 Image filtering
Feature detection and matching
3 Segmentation
Feature-based alignment
4 Structure from motion
Image stitching
5 Computational photography
Face detection and object recognition
6 Neural network, Deep Learning, and CNN
PyTorch introduction
7 TensorFlow introduction
Application: human pose estimate
8 Embedded computer vision and optimization
Your Instructor
 Eugene Chang
  • PhD Univ of Texas at Austin 1993 Computer Engineering
  • MS, ECE UC Santa Barbara
  • Director Computer Vision at Magic Leap
  • Past Experience of teaching at Silicon Valley University