Invited Talk at Muroran Institute of Technology (Co-organized)
An invited talk by Prof. Takamichi Miyata, Professor, Chiba Institute of Technology, Japan, will be held on May 24, 2024, in Room R205, Education & Research Building No. 8, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran, Hokkaido, 0508585 Japan. Prof. Takamichi Miyata will share some interesting ideas about Estimating and improving image quality for humans and AI using optimization, generative models, and vision language models.
CO-ORGANIZED BY:
IEEE Muroran Institute of Technology Student Branch
IEEE Sapporo Section Young Professionals (YP)
Emerging Networks and Systems Laboratory (ENeS), Muroran Institute of Technology
Date and Time
Location
Hosts
Registration
- Date: 24 May 2024
- Time: 11:30 AM to 12:30 PM
- All times are (GMT+09:00) Japan
-
Add Event to Calendar
- 27-1 Mizumoto-cho, Muroran, Hokkaido
- Muroran, Hokkaido
- Japan 0508585
- Building: R205
- Starts 24 May 2024 11:15 AM
- Ends 24 May 2024 11:30 AM
- All times are (GMT+09:00) Japan
- No Admission Charge
Speakers
Prof. Takamichi Miyata of Chiba Institute of Technology, Japan
Estimating and improving image quality for humans and AI using optimization, generative models, and vision language mode
The widespread use of smartphones has made it common for us to communicate using images in our daily lives. Furthermore, in recent years, images are used not only for communication between humans, but also for various advanced decisions using AI. Degradation of these images due to noise generated during image acquisition and compression coding can degrade the quality of communication using these images and the recognition accuracy of AI. This presentation will introduce the results of research to date related to estimating the perceptual quality of images containing degradation and removing the degradation. Mathematical optimization such as tensor restoration, as well as how deep learning, especially diffusion image generation models and vision language models, can be applied to this task will be explained in detail.
Biography:
Takamichi Miyata received B.E. and M.E. degrees from the University of Toyama in 2001 and 2003, respectively, and a Ph.D. degree from the Tokyo Institute of Technology in 2006, where he joined as an Assistant Professor. From 2012 to 2014, he was an Associate Professor with the Chiba Institute of Technology, where he has been a Professor since 2014. His current research interests include image processing. He received the Excellent Paper Award from the IEICE in 2013.
Address:Japan