Imaging Systems have progressed a lot in the last several decades. With the advent of Machine Learning (ML) and Artificial Intelligence (AI), new imaging paradigm have evolved rapidly. In this talk, I will present few of my works based on these approaches. Firstly, I would present a reconfigurable imaging system which learns from its surrounding physical world data and adapts itself. I will present a novel modular multi-modal adaptive imaging platform, driven by AI, which acquires portions of the scene at high quality and rest at lower quality to optimize end task. This imaging system specifically caters to high resolution imaging sensors with low compute power and constrained channel bandwidth between host and the chip. Secondly, I would present a novel physics-based machine learning model which can characterize the radiation semiconductor image sensor such as CdZnTe non-homogenously in a voxelated manner. This approach has been shown in 1D, 3D as well as with reduced data than what is dictated by physical equations. Thirdly, I would present the computational imaging approach using Scanning Transmission X-ray Microscopy (STXM) coupled with vector Tomography to image 3D magnetic domains at nanoscale. Lastly, I would touch upon some of my contributions made in the domain of Neuromorphic Computing Algorithms in the realm of object detection and tactile sensing.

To add to calendar:

Click on:  https://wordpress.cels.anl.gov/cels-seminars/

Enter your credentials.

Search for your seminar 

Click “Add to calendar”