Developing Computer Vision Applications Part 2:
Computer Vision in Depth
Date: On Demand
Duration: 41 Hours
This course covered Computer Vision in depth and to equip the participant with the skills to develop CV Applications using open source tools and work on images.
At the end of the course, the participants will be able to:
- Mathematical Foundations
- Image Acquisition
- Image formation: visible light, other EM spectrum
- Color spaces
- image compression
- Point processing
- Histogram equalization, Contrast enhancement
- Neighborhood processing
- Convolution, Edge detection, Blurring, Noise filtering
- Geometric transformations
- Affine transformations, Homographies
- Machine Learning Algorithms – Classification & Regression
- Training, testing, validation, feature extraction
- Machine Learning Algorithms – Deep Learning
- CNN, LSTM, RNN, GAN, VAE
Who Should Attend
Computer Vision Engineers and Specialists
(Click their photos to view their short biographies)
Dr Natarajan Prabhu
Dr Natarajan Prabhu is currently a lecturer in the School of Computing at the National University of Singapore. He has 10+ years of experience in teaching for master’s degree programs, undergraduate modules, and continuing education courses. Before joining NUS, he was teaching at DigiPen Institute of Technology, where he taught AI for Games, Digital Image Processing, Machine Learning, Deep Learning, Data Structures, etc. In DigiPen, he developed a master’ degree program for Computer Vision that primarily prepares graduate students to work in the CV industry. After joining NUS as a lecturer, he is currently working on developing and teaching an AI module for non-CS students in Blended learning.
He graduated with a Ph.D. degree from NUS in 2013, a master’s degree, and a bachelor’s degree from Anna University in 2008 and 2006, respectively. His Ph.D. thesis was about automatically controlling and coordinating multiple active cameras in surveillance networks. During this time he has gained rich experience in building multi-camera surveillance systems. He has received “Best PhD Forum Paper” award from International Conference on Distributed Smart Cameras (Hong Kong, 2012) and “Research Achievement Award” from School of Computing, NUS (2012).
Assoc Prof Terence Sim
Explain. Demonstrate. Experiment. Inspire.
The above sums up Dr Terence Sim’s teaching and research philosophy. Over the years, Dr Sim has had the pleasure of teaching many courses – Introductory Programming, Computer Vision and Pattern Recognition, Digital Visual Effects, Theoretical Foundations of Multimedia, Analysis of Multimedia – and interacting with many talented students. He is currently teaching a freshmen module in Discrete Structures, and a graduate module in Biometrics Authentication.
For research, Dr Sim explores several areas related to Visual Computing: Facial image analysis, Multimodal biometrics, Facial rendering, Computational photography, Continuous authentication, Music transcription, to name a few. He combines machine learning with physics-based modeling and graphics rendering to tackle the challenges in research. Dr Sim also provides consultancy in biometrics, which can be in the form of training, feasibility study, or technical assessment.
Dr Sim has published over 100 papers in top international journals and conferences. He is active both as Reviewer and as Senior Program Committee Member in numerous conferences. He is also an IEEE Member. He served as President of the Pattern Recognition and Machine Intelligence Association in Singapore from 2014 to 2016, and was also Vice President from 2010 to 2014. Dr Sim also strongly believes in International Standards and served as Chairman of Workgroup 6: Cross-Jurisdiction and Societal Issues of the Biometrics Technical Committee in Singapore from 2006 to 2014.
Dr Sim considers it a blessing and privilege to have attended, and graduated from three top universities in the world: He obtained his Bachelor of Science in Computer Science and Engineering in 1990 from the Massachusetts Institute of Technology (MIT), his Master of Science in Computer Science in 1991 from Stanford University, and his Doctor of Philosophy in Electrical Engineering in 2002 from Carnegie Mellon University.
Assoc Prof Ng Teck Khim
Assoc Prof Ng Teck Khim is an associate professor of practice in the School of Computing, National University of Singapore.
My research interest is mainly in geometrical computer vision such as 3D reconstruction from images and other geometry related computer vision topics. Application wise, I am interested in computer vision related technologies such as Markerless Augmented Reality (AR) and sports video analytics. I obtained my Ph.D. from Carnegie Mellon University in 1999. My thesis topic was on reconstructing 3D large scenes from 2D images. My bachelor and master degree education was obtained from National University of Singapore, in 1992 and 1988 respectively.
I was with the defence R&D for the Ministry of Defence of Singapore for almost my entire career before joining NUS. I also served a year in Media Development Authority as a Program Director in the Interactive Digital Media R&D Programme Office in 2007/8. Prior to joining NUS, I was the Head of Signal Processing Lab, DSO National Laboratories Singapore. My lab was doing image processing, computer vision and audio processing research for military applications.
Total Nett Programme Fee Payable, Including GST, after additional funding from the various funding schemes
Participants must fulfill at least 75% attendance and pass all assessment components to be eligible for SSG funding.
To enquire, email firstname.lastname@example.org
To register, click Register
Select Short Course / Modular Course -> Apply for Myself -> Browse Academic Modules / Short Courses-> Module/Course Category -> Short Courses -> Browse Courses-> Strategic Tech Mgt Institute (Faculty/Department / Unit)
Please download the user guide for NUS Online Application Portal after you click ‘Apply for Myself’ if you need assistance.
Course Fee Breakdown
Singapore Citizens39 years old or younger
Singapore Citizen40 years old or older