NEW SC16: Classical and Deep Learning-based Computer Vision
Monday 27 January • 8:30 – 12:45
Course Length: 4 hours
Course Level: Intermediate
Instructor: Richard Xu, University of Technology Sydney

Learning Outcomes
This course enables the attendee to:

• Understand several important aspects and tasks in computer vision.
• Explain why computer vision is challenging
• Explain the role deep learning plays in computer vision.
• Be able to apply OpenCV and TensorFlow 2.0 to build CV models, including object classification, object detection, face recognition, generating synthetic images, and image-to-text.

Computer Vision (CV) is an important application of Artificial Intelligence and Machine Learning models. CV concerns techniques to help computers to “see” and “understand” the content of still images (photos) and sequences of images (videos) and often in the modern context, to combine visual info with other media: e.g., text-to-image and/or image-to-text. In this course, our aim is to teach participants both the classical and modern treatments in computer vision: from camera anatomy (e.g., camera calibration) to manually designed filters (for example, scale-invariant-feature-transform) to powerful modern-day deep learning approach to computer vision.

Intended Audience
Professionals and academics with some background in computer science or programming who are interested in entering the field of computer vision.

Richard Xu is an associate professor in machine learning and a leading researcher in the fields of machine learning, deep learning, data analytics, and computer vision. He is the founder and director of the UTS DataLounge, which provides customised short courses for organisations seeking expertise in the field of machine learning. Xu is also a core member of the Innovation in IT Services and Applications research centre and the Global Big Data Technologies research centre, both at UTS.