COMP4423 Computer Vision

Computer Vision (CV) for beginners at the Hong Kong Polytechnic University.

1. What do we learn?

“Learning CV by playing it.”

We mainly focus on the following topics:

• Image Processing
• Feature Extraction
• Image Retrieval Fundamentals
• Image Classification Fundamentals
• Traditional Machine Learning to Deep Learning
• Deep Image Retrieval
• CAM, Attentions and Transformers
• Detection & Segmentation
• Learning Paradigms
• Large Models
• and more…

You can find more information, such as the pre-requisite, in the official Subject Description Form here.

You can find learning details, slides, videos, codes and other resources here.

2. What have we done?

2.1 Sign Language Recognition

• Sign Language Recognition System by Support Vector Machines (SVM)

2.2 Campus Tour Guide

• A Campus Tour Guide with On-campus Landmarks Recognition System

2.3 Fashion Image Generation

• Fashion Image Generation by Generative Adversarial Networks (GANs) on Fashion MNIST

3. What is next?

In this course, we not only learn the basic knowledge of computer vision but also apply and transform the knowledge into practical projects as well as further research topics.

Rubing Chen, Wengyu Zhang, and Yiyang Jiang, as year 2 undergraduate students, took the course in 2023, and Tianyi Zhang, as a year 3 undergraduate student, took the course in 2024. They have further joined the PolySmart Group as student assistants for research and engineering projects.

You can find more information about the student’s development and achievements here.