Coded Aperture Compressive Spectral and Temporal Imaging
15 Apr 2013 | Online Presentations | Contributor(s): Lawrence Carin
In this talk we examine how modern statistical tools may be used to achieve remarkable levels of compression directly at the measurement point, with demonstrations based on new hyperspectral and video cameras. The talk will examine the fundamental mathematics and statistics, and show results...
Data-adaptive Filtering and the State of the Art in Image Processing
15 Apr 2013 | Online Presentations | Contributor(s): Peyman Milanfar
In this talk, I will present a practical and unified framework for understanding some common underpinnings of these methods. This leads to new insights and a broad understanding of how these diverse methods interrelate. I will also discuss the statistical performance of the resulting algorithms,...
Integrated Imaging: Creating Images from the Tight Integration of Algorithms, Computation, and Sensors
21 Apr 2015 | Online Presentations | Contributor(s): Charles Addison Bouman
This talk presents some examples of state-of-the-art integrated imaging systems based on computed tomography (CT), transmission electron microscopy (STEM), synchrotron beam imaging, optical sensing, and scanning electron microscopy (SEM). For each of these examples, we also explore their use and...
Computational Imaging From Nanoscopic to Astronomical Scales
29 Jun 2017 | Online Presentations | Contributor(s): Oliver S. Cossairt
In this talk, I will provide an overview of computational imaging technologies under development by the NU Comp Photo Lab, covering a large span of physical scales: from the nanoscopic to the astronomic. First, I will introduce a Synthetic Aperture Visual Imaging (SAVI) technique to image at...
Computational Imaging for Optical Super-resolution and Source Separation
19 Sep 2017 | Online Presentations | Contributor(s): Aswin C. Sankaranarayanan
I will discuss a few examples from my research including high-resolution imaging in infrared, extremely with thin form-factor cameras, and enabling post-process freedom in manipulating photographs. In each example, I will discuss research from my work on novel imaging designs and associated...
Imaging Sciences at the Oak Ridge National Laboratory: Identity Sciences, Advanced Manufacturing, Computational Imaging, Machine Learning, and Super Computing
03 Jan 2019 | Online Presentations | Contributor(s): Hector J. Santos-Villalobos
Dr. Santos takes us on the journey of working at the Oak Ridge National Laboratory as an imaging scientist. He showcases work in the areas of Identity Sciences (i.e., biometrics), Machine Learning, and Computational Imaging. Some application to discuss are coded source neutron imaging, non-ideal...
Unveiling Convolutional Neural Networks (CNNs) through An Interpretable Design
03 Jan 2019 | Online Presentations | Contributor(s): C.-C. Jay Kuo
We attempt to unveil the working principle of simple convolutional neural networks (CNNs) through a constructive, feedforward and interpretable design in this work. A CNN is simple if it is a cascade of two networks, where the first one consists of convolutional layers and the second one contains...