Computer Vision: Machine Learning-based Face Recognition, Autonomous Driving, and Image Processing

Course 11: Computer Vision: Machine Learning-based Face Recognition, Autonomous Driving, and Image Processing

I. Course Description

Computer vision is a core discipline of artificial intelligence, which trains machines to explain the visual world. Using digital images from the camera and video, the computer can identify, classify objects as well as analyze motion. This technology plays an important role in a number of applications, including video surveillance, media content analysis, robotics, autonomous driving, and biomedical research. An initial presentation of the topic is appropriate for undergraduates with a background in computer science, mathematics, or engineering.

This course will cover how to deal with digital images and videos. Teaching materials will revolve around core concepts such as feature extraction, segmentation, deprotection of objects, and analysis of visual motion. The course will answer how neural networks and deep learning have revolutionized the field of computer vision. Thus, this course provides an excellent opportunity to learn the application of machine learning in the environment. The goal of this course is to apply the material to a specific project. Here, you will learn how to study a specific problem, design and implement a solution, and evaluate the performance of the developed algorithm. Each group will record their work in a written report. In this way, you will gain experience with academic research and learn how to write a research report. The research directions include but are not limited to: face recognition, autonomous driving, microscope data, graphics art, etc. Throughout the course, the Python will be used as a programming language, with additional references and readings provided for each session.

II. Professor Introduction

Jens Rittscher – Tentenured Professor at Oxford University

Jens Rittscher Currently working at the University of Oxford, he is the first jointly appointed professor at the School of Biomedical Engineering and Nuffield School of Medicine. He is also a tenured Professor of Engineering at Oxford University, a member of the Ludwig Cancer Institute and the Wellcome Human Genomics Center, Oxford University, and the team leader of the Oxford Big Data Institute. Prior to joining Oxford, Jens joined General Electric after completing his PhD at Oxford and served as a Senior Senior Fellow / Project Manager at its Global Research Center, leading its Computer Vision Laboratory.

In 2019, he co-founded Ground Truth Labs Ltd with others to commercialize computational pathology research in his laboratory. Previously, Jens served as the IEEE ISBI Steering Committee Chairman. Currently, he is the co-director of the EPSRC Health Data Science and has joined the UK EPSRC Medical Technology Strategy Advisory Group since 2021.

III. Syllabus

1. Introduction and background of computer vision
2. Image segmentation
3. Image features and registration
4. Machine-learning concepts
5. Object detection and classification
6. Introduction to deep learning and object detection
7. Segmentation and image generation
8. Advanced topics of deep learning
9. Visual motion and tracking
10. Biomedical image analysis