U.S. flag

An official website of the United States government, Department of Justice.

Dot gov

The .gov means it’s official.
Federal government websites always use a .gov or .mil domain. Before sharing sensitive information online, make sure you’re on a .gov or .mil site by inspecting your browser’s address (or “location”) bar.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Incorporating Graph-Based Models in a Deep Learning Framework for Operational Face Recognition

Award Information

Awardee
Michigan State University
Award #
2015-R2-CX-0005
Location

East Lansing, MI

Awardee County
Ingham
Congressional District
8
Status
Closed
Funding First Awarded
2015
Total funding (to date)
$150,000
Original Solicitation
NIJ FY 15 Graduate Research Fellowship Program in Science, Technology, Engineering, and Mathematics

Description of original award (Fiscal Year 2015, $50,000)

This award was competitively made in response to a proposal submitted by Michigan State University to a National Institute of Justice FY 2015 solicitation: “Graduate Research Fellowship in Science, Technology, Engineering & Mathematics.” With this solicitation, NIJ sought applications for funding innovative doctoral dissertation research in science, technology, engineering, or mathematics that is relevant to providing solutions to better ensure public safety, prevent and control crime, and ensure the fair and impartial administration of criminal justice in the United States. The ultimate goal of this solicitation is to increase the pool of researchers in science, technology, engineering, and mathematics fields who are involved in research relevant to criminal justice applications. In its application, Michigan State University proposes to improve the process of automated face recognition by wrapping into the process demographic information such as known associates, gender and social networking data. This application 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. It is proposed that 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 is being funded incrementally in 3 phases, with the effort funded in FY15 representing the first phase.

This project contains a research and/or development component, as defined in applicable law.

ca/ncf

As submitted by the proposer: 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, we propose 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. Experimental evaluation will be conducted on large datasets. ca/ncf

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.

nca/ncf

Date Created: September 15, 2015