An Evaluation of Bimodal Recognition Systems Based on Voice and Facial Images

Author: Abel Sebastián Santamarina Maciá

Original title: An Evaluation of Bimodal Recognition Systems Based on Voice and Facial Images

Language: English

Electronic version: Portuguese| English

Abstract

The main objective of this dissertation is to compare the most important approaches for score-level fusion of two unimodal systems consisting of facial and speaker recognition systems. Two classification methods for each biometric modality were implemented: a GMM/UBM and an I-Vector/GPLDA classifiers for speaker recognition and a GMM/UBM and LBP-based classifiers for facial recognition, resulting in four different multimodal combination of fusion explored. The score-level fusion methods investigated are divided in Density-based, Transformation-based and Classifier-based groups and few variants on each group were tested. The fusion methods were evaluated in verification mode, using two different databases, one virtual database and a bimodal database. The results of each bimodal fusion technique implemented were compared with the unimodal systems, which showed significant recognition performance gains. Density-based techniques presented the best results among all fusion approaches, at the expense of higher computational complexity due to the density estimation process.