Computer Vision 2023

Fall 2023, Thur. 1:10pm to 4:00pm, Location: Engineering Building Room 302
Instructor: Chih-Yuan Yang

Course Information

In this course, I will introduce fundamental concepts of computer vision. I expect students can understand a few important topics in computer vision such as image processing, color spaces, recognition, convolutional neural networks, generative models, vision-language models. Through discussion in the class and implementation for projects, students should learn concepts and first-hand experience of applying computer vision knowledge for real-world applications.

The course consists of four programming projects and one final group project (max 5 members each team). Please find information about final project in the syllabus.

Prerequisites

This course requires programming experience as well as linear algebra, basic calculus, and basic probability. Previous knowledge of visual computing will be helpful.

Syllabus

Week	Date	Topic	Slides	Recording	Action
1	9/7	Introduction to computer vision, camera, human vision	pptx	video
2	9/14	Human vision, color, digital camera, image filtering,	pptx	video
3	9/21	Fourier transform, image pyramid, aliasing, JPEG compression	pptx	video	Team member list
4	9/28	Applications of Fourier transform, computing resources of CGU AI Center	pptx	video	Homework1 presentation
5	10/5	Homework 1 feedback, CGU AI center Kubeflow demo, deep learning for computer vision	pptx	video	Project proposal due
6	10/12	Project pitch feedback, k-nearest neighbor, k-fold cross validation	pptx	video	Project pitch
7	10/19	CGU AI center computing resource tutorial for DNN training and image generation	pptx	video	Homework2 presentation
8	10/26	HOG-based pedestrian detection, CNN-part 1: linear classifier, regulation and optimization	pptx	video
9	11/2	CNN-part 2: Neural networks, backpropagation, convolutional neural networks	pptx	video
10	11/9	CNN-part 3: 1x1 convolution	pptx	video	Homework3 presentation
11	11/16	Homework 3 feedback, 3D convolution, generative model part1: GANs	pptx	video	Project midterm report
12	11/23	Generative model part2: GANs, Diffusion model, CLIP	pptx	video
13	11/30	Students’ Homework4 Presentation			Homework4 presentation
14	12/7	Transformer, ViT, CLIP, LAION, DDPM, DDIM, AE, VAE, VQ-VAE	pptx	video
15	12/14	SAGAN, BigGAN, BERT, Network-to-Network, VQGAN, DALL-E, Latent Diffusion, OpenCLIP, PyramidCLIP	pptx	video
16	12/21	Final presentation, BLIP	pptx	video	Term project presentation

Term Project Topics, Slides, and Reports

Topic	Slides	Report
Deepfake Detection: An In-depth Comparative Analysis of the Generalizability of Various Deepfake Detection Techniques	pptx	docx
Visual Inspection on Mango Maturity	pptx	pdf
Impact of Lighting Conditions on Face Recognition Accuracy	pptx	pdf
Sign Language Translation System	pptx	docx
Social Distance Detection	pptx	pdf

Instructor’s comments on the final reports pdf

Textbook

• Computer Vision: Algorithms and Applications by Richard Szeliski (2022)
  It is available online for free.

Reference Books

• Available online for free offered by the authors.
  • Programming Computer Vision with Python: Tools and algorithms for analyzing images by Jam Solem. (2012)
  • Deep Learning by Ian Goodfellow et al. (2016). A third-party-made PDF is available at GitHub.
  • Computer Vision: Models, Learning, and Inference by Simon J.D. Prince. (2012)
  • Data Driven Science and Engineering by Steven L. Brunton and J. Nathan Kutz. (2017)
  • Learn Computer Vision Using OpenCV With Deep Learning CNNs and RNNs by Sunila Gollapudi (2019)
• No free PDF offered by the authors, but available at school library.
  • Digital Image Processing 3th edition by Rafael Gonzalez and Richard Woods. (2008) There is a 4th edition published in 2017.
  • Digital Image Processing using Matlab 2nd edition by Rafael Gonzalez et al. (2010)
  • Learning OpenCV3 by Adrian Kaehler & Gary Bradski. (2017)
• No free PDF offered by the authors, but code available at GitHub.
  • OpenCV 3.x with Python By Example 2nd edition by Gabriel Garrido and Prateek Joshi. (2018)

Existing Full-length Course Lecture Recordings

• MIT 6.S191: Introduction to Deep Learning 2023
• NTHU EE 6485 Computer Vision 2022
• UMich EECS 498-007: Deep Learning for Computer Vision 2019
• MIT 6.S094: Deep Learning for Self-Driving Cars 2018
• Stanford CS231n: Deep Learning for Computer Vision 2017
• UCF CAP5415: Computer Vision 2014

Existing Online Lecture Videos for Computer Vision Knowledge Points

• Columbia Computer Science 2021

Existing Computer Vision Course Slides for Self-Learning

• Alexei Efros at UC Berkeley https://cs280-berkeley.github.io/
• Derek Hoiem at UIUC https://courses.engr.illinois.edu/cs543/sp2017/
• David Forsyth at UIUC http://luthuli.cs.uiuc.edu/~daf/courses/CV23/planned.html
• James Hays at Georgia Tech https://faculty.cc.gatech.edu/~hays/compvision2022fall/
• Steve Seitz at U Washington https://courses.cs.washington.edu/courses/cse576/20sp/calendar/
• Min Sun at NTHU https://aliensunmin.github.io/teaching/cv2022/index.html
• Justin Johnson at UMich https://web.eecs.umich.edu/~justincj/teaching/eecs498/WI2022/

School e-Learning Link

CGU e-Learning site

Grading

Your final grade will be made up from

• 60% 4 pieces of programming homework
• 35% term project, including proposal (5%), project pitch (5%), midterm report (5%), final project presentation (10%), and final project report(10%). Maximum 5 members each group.
• 5% class participation
• late policy
  You will lose 10% each day for a late submission. However, you have three “late days” for the whole course. That is to say, the first 24 hours after the due date counts as 1 day, up to 48 hours is two and 72 for the third late day. After running out of the three “late days”, I will deduct the penalty from your points.

Contact Info and Office Hour

Chih-Yuan Yang: cyyang@cgu.edu.tw
Office hours: Tue 10:30~11:30 Management Building Room 1416