Speakers
Abstract: Through a very simple fringe denoising example, we investigate that (i) what are the behaviours of the existing machine learning algorithms? (ii) can we propose a wiser machine learning-based solution? (iii) do these algorithms perform better than a traditional algorithm? (iv) Why do they win or lose the comparison? The aim of such investigation is to deepen our understanding of the pros and cons of using machine learning for metrology tasks.
Dr Qian Kemao is an Associate Professor in the College of Computing and Data Science (CCDS) at Nanyang Technological University (NTU). He got his BE, ME and PhD degrees from University of Science and Technology of China (USTC). His research interests include optical metrology, image processing, parallel computing, and computer vision. He co-chaired icOPEN and COME conferences for several times.