Abstract: X-ray micro-tomography ($\mu$-CT) is a non-destructive 3D imaging technique often used to image material samples. Synchrotron-based $\mu$-CT instruments, such as the Advanced Light Source at Berkeley National Laboratory, produce high volumes of data at a fast rate. This prompts the need for image processing techniques capable of extracting valuable information quickly in large complex data sets. Image segmentation is one such processing technique which separates various components in an image. Graph-based segmentation algorithms have been used for many years; recent approaches using Markov Random Fields (MRFs) exploit local properties of MRFs to run computations in parallel. In this talk, we will discuss a hypergraph-based MRF model used in the development of a robust, parallelizable image segmentation algorithm. This project is the result of the Department of Energy’s Visiting Faculty Program in collaboration with Dr. Talita Perciano from Lawrence Berkeley National Laboratory, and Stanislaus State undergraduate students Darcy Brunk, Juan Valencia, and Sherly Yaghoubi