HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE

Department of Computer Science Seminar
2018 Series

Image Quality Assessment: Facing the Real-World Challenges

Dr. Kede Ma
Research Associate
Howard Hughes Medical Institute
Laboratory for Computational Vision
New York University
USA

Date: November 7, 2018 (Wednesday)
Time: 10:30 - 11:30 am
Venue: FSC703, Fong Shu Chuen Library, Ho Sin Hang Campus

Abstract
Image quality assessment (IQA) aims to quantify the human perception of image quality, which is a fundamental problem in image processing and computer vision. While the recent development of objective IQA is worth celebrating, many challenges remain when we apply existing IQA models in real-world applications.

In this talk, I will discuss three real-world challenges in IQA and present solutions to them: (1) Group Maximum Differentiation Competition. How to test the generalizability of objective IQA models on a large-scale image database with no human annotations? (2) Deep Learning for IQA. Is it possible to learn deep neural networks for IQA from a small number of human annotations? How to incorporate biologically plausible components to reduce network complexity? (3) Multi-Exposure Image Fusion (MEF). What is the role of IQA in such a specific image processing application? How to design better MEF methods from quality assessment to perceptual optimization? Finally, I will introduce other real-world challenges in IQA and point out some promising future directions.

Biography
Kede Ma is a Research Associate with the Howard Hughes Medical Institute and the Laboratory for Computational Vision, New York University, New York, NY, USA. He received the Ph.D. degree in electrical and computer engineering from the University of Waterloo, Waterloo, ON, Canada, in 2017 and the B.E. degree from the University of Science and Technology of China, Hefei, China, in 2012. From 2015 to 2016, he was a Visiting Scholar with the Department of Computing, The Hong Kong Polytechnic University. His research interests span perceptual image processing, computational vision, and computational photography. He has more than 20 publications at prestigious journals and conferences, such as IEEE T-IP, T-IFS, T-CI, and CVPR with over 1,000 citations (Google Scholar).

********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)

http://www.comp.hkbu.edu.hk/v1/?page=seminars&id=494&lang=tc
Photos  Slides