Optimization of an individual re-identification modeling process using biometric features

We present results from the optimization of a reidentification process using two sets of biometric data obtained from the Civilian American and European Surface Anthropometry Resource Project (CAESAR) database. The datasets contain real measurements of features for 2378 individuals in a standing (43 features) and seated (16 features) position. A genetic algorithm (GA) was used to search a large combinatorial space where different features are available between the probe (seated) and gallery (standing) datasets. Multiple linear regression models are employed to estimate one set of features from the other. Results show that optimized model predictions obtained using less than half of the 43 gallery features and data from roughly 16% of the individuals available produce better reidentification rates than two other approaches that use all 43 gallery set features and information from all 2378 individuals.