Label Propagation Approach for Predicting Missing Biographic Labels in Face-based Biometric records

• NCJ Number: 253424
• Author(s): Thomas. Swearingen; Arun Ross
• Date Published: January 2018
• Length: 10 pages
• Grant Number(s): 2015-R2-CX-0005
• Agencies: NIJ-Sponsored
• Publication Type: Research (Applied/Empirical); Report (Study/Research); Report (Grant Sponsored); Program/Project Description
• Award: Incorporating Graph-Based Models in a Deep Learning Framework for Operational Face Recognition

Annotation

This article proposes the use of a graph structure to model the relationship between the biometric records in a database showing the benefits of such a graph in deducing biographic labels of incomplete records, i.e. records that may have missing biographic information.

Abstract

A biometric system uses the physical or behavioral attributes of a person, such as face, fingerprint, iris, or voice, to recognize an individual. Many operational biometric systems store the biographic information of an individual, viz., name, gender, age and ethnicity, besides the biometric data itself. Thus, the biometric record pertaining to an individual consists of both biometric data and biographic data. The current project used a label propagation scheme to deduce missing values for both binary-valued biographic attributes (e.g. gender) as well as multi-valued biographic attributes (e.g. age group). Experimental results using face-based biometric records consisting of name, age, gender and ethnicity convey the pros and cons of the proposed method. (publisher abstract modified)