Course Introduction
- Course Name: Computer Vision
- Course Code: CII4Q3
- Credits : 3
- Elective course on Artificial Intelligence Track
- Focused in the practical implementation of Modern Computer Visions
Prerequisite: Basic Knowledge Required
- Proficiency in Algorithm and Programming
- Calculus, Linear Algebra
- Artificial Intelligence
Prerequisite: Equivalent knowledge
- Digital Image Processing
- Machine Learning
Course Objective
- Specific materials aimed to support your thesis
- Covering Machine Learning research and developments, with specific examples on Computer Vision
Points
- CLO 1 : understand the basic concepts of visual object recognition systems
- CLO 2 : implement a visual object recognition system using a machine learning-based approach
- CLO 3 : implement a visual object recognition system using a deep learning-based approach
Point Distribution
A | 80 … 100.0 |
AB | 75 … 79.9 |
B | 70 … 74.9 |
BC | 60 … 69.9 |
C | 50 … 59.9 |
D | 40 … 49.9 |
E | 0 … 39.9 |
Course Reference
Lecture Slides
- 01 – Introduction
- 01 – Introduction pt2: History of Computer Vision
- 01 – Introduction pt3: Recognition and Detection
- 02.1 – Visual Recognition System
- 02.2 – Hyperparameter and Data Handling
- 02.3 – Linear Classification
- 03.1 – Neural Network
- 03.2 – Convolutional Neural Network
- 04 – Digital Image Processing
- 05.1 – Filtering
- 05.2 – Edge Detection
- 06.1 – Feature and Detectors
- 06.2 – Feature Descriptors
- 07.1 – Feature Learning
- 07.2 – ConvNets Architectures [2012-2014]
- 07.3 – ConvNets Architectures [2015-2018]
- 08.1 – Visualizing Weights
- 08.2 – Visualization via Optimization
- 09.1 – Deep Dream and Style Transfer
- 09.2 – Variational AutoEncoder
- 09.3 – Generative Adversarial Network
- 10.1 – Object Localization
- 10.2 – Classical Object Detection
- 10.3 – Two-Stage Object Detection
- 10.4 – One-Stage Object Detection
- 11.1 – Classic Image Segmentation
- 11.2 – Modern Image Segmentation
- 12.1 – Recurrent Neural Network
- 12.2 – Image Captioning
Exercises
- 00 – Introduction
- 00 – Nearest Neighbors
- 01 – Linear Classification
- 02 – Image Features
- 03 – Neural Network
- 04 – TensorFlow
- 05 – Convolution
- 06 – Augmentation
- 07 – Filtering and Edge Detection
- 08 – CNN Architectures
- 09 – Keras Model
- 10 – Transfer Learning
- 11 – PyTorch
- 12.1 – Network Visualization (PyTorch)
- 12.2 – Network Visualization (TensorFlow)
- 13 – Neural Style Transfer (PyTorch)
- 14 – Generative Adversarial Network (PyTorch)
- 15 – You Only Look Once Object Detection
- 16 – Object Segmentation
- 17 – Recurrent Neural Net
- 18 – Long Short Term Memory
Lecture Viewer
Teaching History
- 2020