This awardee has received supplemental funding. This award detail page includes information about both the original award and supplemental awards.
Description of original award (Fiscal Year 2015, $50,000)
In classical face recognition, an input probe image is compared against a gallery of labeled face images in order to determine its identity. In most applications, the gallery images (identities) are assumed to be independent of each other, i.e., the relationship between gallery images is not exploited during the face recognition process.
In this work,the researcher proposes a graph-based approach in which gallery images are used to generate a powerful network structure where the nodes correspond to individual identities (and consist of face images as well as biographic attributes such as gender, ethnicity, name, etc.) and the edge weights define the degree of similarity between two such nodes. This network can 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 probe image based on label propagation schemes; (c) to perform rapid 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 nodes that have strong edges.
This project contains a research and/or development component, as defined in the applicable law.
- Developing a Portable and Fast Opioid Assessment Tool for Improved Field Decision-Making
- Community-Led Learning: A Collaborative Approach to Training and Technical Assistance for Violent Crime Problem Analyses
- Nanoparticle-Decorated Micropillars As Integrated Raman Spectroscopy and Mass Spectrometry Substrates for Quantitative and High-Throughput Toxicology Drug Analysis