Convolutional sparse coding based regularizers for tomographic inverse problemsMS11

Regularized/model-based inversion techniques have emerged as a vital tool in improving tomographic reconstruction quality for microscopic applications. In this talk, we will present an algorithm for integrating data-driven regularizers based on convolutional sparse representations into the tomographic reconstruction framework. We will present results of using these techniques on scientific tomography data sets and compare them to the traditional regularizers used in these applications.

This presentation is part of Minisymposium “MS11 - Computational Imaging for Micro- and Nano-structures in Materials Science (2 parts)
organized by: Brendt Wohlberg (Los Alamos National Laboratory) , Jeff Simmons (Air Force Research Laboratory) .

Singanallur Venkatakrishnan (Oak Ridge National Laboratory)
Brendt Wohlberg (Los Alamos National Laboratory)
computed tomography, image enhancement, image reconstruction, machine learning