Computer Vision
Objective
Course Aim and Objectives
Computer vision is an important and one of the most active sub-domain and research area of Artificial Intelligence (AI) and focuses on the development of tools, techniques and algorithms required to re-create human vision apparatus.
The objective of this course is to develop understanding of the principles and techniques of image processing, image analysis, image understanding and computer vision. This course is focused on the latest trends in computer vision and emphasizes on the applications of machine learning / deep learning.
To understand different concepts discussed in this course, students are expected to have strong familiarity with concepts of linear algebra, probability theory, analytical geometry and multivariate calculus. Familiarity with image processing is desirable but not mandatory.
Announcement
If you would like to acknowledge my efforts or to send feedback, please email me: Rizwan17 {AT} gmail {DOT} com
Course Contents
Week
Module
Topics
Reading / Reference Material
Lecture Notes / Video Recording
Image Processing and Early Vision
1 - 2
Introduction to Computer Vision
What is visual Intelligence
From Human Vision to Computer Vision
Image formation and representation
Basic Image manipulation
Histogram
Contrast Stretching
Histogram Equalization
Intensity Transformation
Image segmentation
Otsu's Algorithm
Chapter 1 and 3: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, latest edition.
Chapter 3: Digital Image Processing, Gonzalez & Woods, Prentice Hall 4th edition.
3 - 4
Image Processing
Filtering – Spatial Domain
Correlation and Convolution
Noise Removal
Uniformly weighted
Gaussian averaging
Image Derivatives / Edge Detection
Prewitt and Sobel
LoG
Canny
.Chapter 3: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, latest edition.
Chapter 3: Digital Image Processing, Gonzalez & Woods, Prentice Hall 4th edition.
Features & Matching
5 - 6
Features and Matching
Key point Detection
Harris Corner Detector
Local Descriptors
SIFT Descriptor
Scale invariance
Keypoint localization
Orientation of keypoints
Descriptor
Matching
Chapter : 7: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, Second edition.
Chapter 11 : Digital Image Processing, Gonzalez & Woods, Prentice Hall, 4th edition.
Chapter 5: Computer Vision: A Modern Approach, Forsyth & Ponce, Pearson, Second
or latest edition.
7
Motion Estimation
Optical Flow
Lecture Slides
Lecture Video
Mid Term Exam Week
Machine Learning for Classification and Image Understanding
9-10
Machine Learning (ML)
Introduction to Machine Learning (ML)
Why ML in Computer Vision?
Types of ML:
Supervised Learning
Unsupervised Learning
Reinforcement Learning
ML Models
Linear Regression
Logistic Regression
Gradient Descent Optimization
Chapter 1: Machine Learning, Tom MITCHELL, McGraw Hill, latest edition.
Chapter 1: Pattern Recognition, S. Theodoridis et al.,Academic Press, 4th or latest edition.
Chapter 5: Speech and Language Processing, Jurafsky and Martin., https://web.stanford.edu/~jurafsky/slp3/
Chapter 5: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, Second edition
11-12
Artificial Neural Networks and Deep Learning
Artificial Neural Network
Convolutional Neural Network
Convolution Layer
Padding
Pooling
Fully connected
Chapter 7: Speech and Language Processing, Jurafsky and Martin., https://web.stanford.edu/~jurafsky/slp3/
Chapter 4: Pattern Recognition, Theodoridis et al., Academic Press, 4th Edition or latest edition.
Chapter 6: Deep Learning, Goodfellow et al., MIT Press book.
Chapter : 6 and Chapter 7: Dive into Deep Learning, Zhang et al., https://d2l.ai/
13
Seminal Convolutional Neural Networks (CNN)
LeNet
AlexNet
VGG
Resnet
Inception
Chapter : 6 Deep Learning, Goodfellow et al., MIT Press book.
Chapter : 6 and Chapter 7 Dive into Deep Learning, Zhang et al., https://d2l.ai/.
Chapter 5: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, Second edition
Lecture Video-1
14
Applications of CNNs: Image Analysis and Understanding
Image Classification
Object Localization
Object Detection
Image segmentation
Chapter 6: Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, Second edition
Lecture Slides
Lecture Video-1
15 Project Week / Review
16
Latest Trends in Computer Vision Seminars
Lecture Slides - 1
Final Exam Week
Reference Books
Computer Vision: Algorithms and Applications, Richard Szeliski.
https://szeliski.org/Book/
Digital Image Processing, Gonzalez & Woods, Prentice Hall.
https://www.amazon.com/Digital-Image-Processing-Rafael-Gonzalez/dp/9353062985
Computer Vision: A Modern Approach, Forsyth & Ponce, Pearson.
https://www.amazon.com/Computer-Vision-Modern-Approach-2nd/dp/013608592X
Deep Learning, Ian Goodfellow et al. MIT Press.
https://www.deeplearningbook.org/
Pattern Recognition, Konstantinos Koutroumbas and Sergios Theodoridi, Academic Press.
https://www.amazon.com/Pattern-Recognition-Sergios-Theodoridis/dp/1597492728
LaTeX Guide
Students are encouraged to write course project report using LaTeX. If you are unfamiliar with LaTex, then you may refer to concise guide that will help you getting started with it. [LaTeX getting started]