作者: Julian Fierrez , Aythami Morales , Ruben Vera-Rodriguez , David Camacho
DOI: 10.1016/J.INFFUS.2017.12.005
关键词: Biometrics 、 Multiple classifier 、 Multimodal biometrics 、 Computer science 、 Architecture 、 Data science 、 Information fusion 、 Exploit 、 Classifier (UML)
摘要: Abstract The present paper is Part 2 in this series of two papers. In 1 we provided an introduction to Multiple Classifier Systems (MCS) with a focus into the fundamentals: basic nomenclature, key elements, architecture, main methods, and prevalent theory framework. then overviewed application MCS particular field multimodal biometric person authentication last 25 years, as prototypical area which has resulted important achievements. Here more technical detail recent trends developments coming from biometrics that incorporate context information adaptive way. These new architectures exploit input quality measures pattern-specific particularities move apart general population statistics, resulting robust systems. Similarly 1, methods here are described way so they can be applied other fusion problems well. Finally, also discuss open challenges play role.