ECE Distinguished Seminar

Speaker: Prof. William Clem Karl (Boston University)

Title: Learning to Make Images / Machine Learning for Computational Imaging

Abstract: Deep learning has become extremely popular in a variety of signal processing and computer visions tasks, ranging from image denoising to speech recognition. The expressive power of deep networks has enabled them to increase the performance possible on this range of tasks, sometimes dramatically. Computational imaging is the process of forming images from coded observations, coupling physical sensing with algorithms and computational resources. Problems such as computed tomography, synthetic aperture radar, and more recently coded optical imaging all are examples. Deep learning is only just beginning to find its way into computational imaging and with it the potential for better image quality and faster image creation. This talk provides an overview of the use of learning methods in computational imaging focusing on tomography as a prototype problem. Recent papers in the area are summarized and placed in context and major themes identified.

Biography: William Clem Karl received the Ph.D. degree in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology. He is currently Professor and Chair of the Electrical and Computer Engineering Department and a member of the Biomedical Engineering Department at Boston University. Dr. Karl's research interests are in the areas computational imaging, statistical signal and image processing, estimation, detection, and medical signal and image processing. He is a Fellow of the IEEE and the AIMBE. Prof. Karl was the inaugural Editor-in-Chief of the IEEE Transactions on Computational Imaging (2014-2017) and the Editor-in-Chief of the IEEE Transactions on Image Processing (2013-2014). He has served many roles in the IEEE including on the Publication Services and Products Board Strategic Planning Committee, the Signal Processing Society Board of Governors, Conference Board, Publications Board, and the Data Science Initiative. He has been on the Steering Committee for the IEEE Transactions on Medical Imaging and served as General Chair for the IEEE International Symposium on Biomedical Imaging.