I. Title:Mathematical methods in image processing and artificial intelligence

II. Presenter: Prof. LI Chunming，University of Electronic Science and Technology of China

III. Time:09:30-11:30, Wednesday, April 8th, 2026

IV. Location: Room 108, Block C, Research Building, Qingshuihe Campus

V. Overview:

In the fields of image processing and artificial intelligence, many fundamental and important problems can be formulated as a problem of minimizing a nonlinear function with variables in a finite dimensional space, or a functional with variables in an infinite dimensional space, such as function spaces, which are some sets of functions satisfying certain properties. In this talk, I will review some classic mathematical methods in computer vision，medical image analysis, and deep learning, especially the powerful methods based on calculus of vatriations and partial differential equations, and some basic concepts and fundamental theories in deep learning. In particular，I will present my original research on forward-and-backward diffusion with applications to image segmentation and denoising. Some interesting demos will be shown in the talk, with applications to image segmentation, image denoising, 3D reconstruction and visualization.

VI. About the Presenter:

LI Chunming is currently a full professor in the school of Information & Communication Engineering at University of Electronic Science and Technology of China (UESTC). He received Ph.D. in Electrical Engineering from the University of Connecticut, USA, in 2005. He did his postdoctoral research at Vanderbilt University Institute of Imaging Science (UVIIS) from 2005 to 2009, and then worked as a research associate at the department of Radiology in University of Pennsylvania until he moved to China and joined UESTC in 2014. Dr. Li’s research interests include image processing, medical image computing, computer vision, computer graphics, and artificial intelligence, with emphasis on the development of innovative algorithms and mathematical models in these fields. He has proposed a series of mathematical models and algorithms for image segmentation, which have been widely used by researchers and engineers in a variety of fields, and published a number of research articles that have been cited by a large number of researchers from all over the world. He was awarded IEEE Signal Processing Society Best Paper Awards in 2013 and 2015 for his two papers published in 2008 and 2010, respectively. In 2020，Dr. Li was elected as IEEE Fellow for his contributions to computer vision and medical image analysis.