MSU PhD Student designated as a NIJ Graduate Research FellowMSU Department of Computer Science and Engineering PhD student Thomas Swearingen has been designated as a NIJ Graduate Research Fellow based on his proposal "Incorporating Graph-Based Models in a Deep Learning Framework for Operational Face Recognition". (PIs: Swearingen and Ross). As a NIJ Graduate Research Fellow, Thomas will receive a stipend from NIJ toward completing his PhD program. A list of past and present Fellows can be found here: http://nij.gov/funding/fellowships/graduate-research-fellowship/pages/past-fellows.aspx. Swearingen's academic advisor is Arun Ross, Associate Professor of Computer Science and Engineering.
In classical face recognition, an input face image is compared against a gallery of labeled face images in order to determine the identity of a person. In most applications, the relationship between gallery images is not exploited during the face recognition process. In this work, a graph-based approach will be adopted to generate a powerful network structure based on gallery images. This network will be used in several different ways: (a) to create clusters of identities based on graph clustering algorithms; (b) to predict the biographic and demographic attributes of an unknown face image based on label propagation schemes; (c) to perform rapid face recognition by restricting the search to only a fraction of the nodes in the graph; and (d) to infer missing information in nodes based on adjacent nodal information.
(Date Posted: 2015-12-07)