Strategies for Exploiting Independent Cloud Implementations of Biometric Experts in Multibiometric Scenarios

Abstract

Cloud computing represents one of the fastest growing areas of technology and offers a new computing model for various applications and services. This model is particularly interesting for the area of biometric recognition, where scalability, processing power, and storage requirements are becoming a bigger and bigger issue with each new generation of recognition technology. Next to the availability of computing resources, another important aspect of cloud computing with respect to biometrics is accessibility. Since biometric cloud services are easily accessible, it is possible to combine different existing implementations and design new multibiometric services that next to almost unlimited resources also offer superior recognition performance and, consequently, ensure improved security to its client applications. Unfortunately, the literature on the best strategies of how to combine existing implementations of cloud-based biometric experts into a multibiometric service is virtually nonexistent. In this paper, we try to close this gap and evaluate different strategies for combining existing biometric experts into a multibiometric cloud service. We analyze the (fusion) strategies from different perspectives such as performance gains, training complexity, or resource consumption and present results and findings important to software developers and other researchers working in the areas of biometrics and cloud computing. The analysis is conducted based on two biometric cloud services, which are also presented in the paper.

Current foveal inspection and previous peripheral preview influence subsequent eye movement decisions

“…These two classes of stimuli have been successfully used to study how meaningful targets affect eye movement behavior ( Xu-Wilson et al., 2009 ; Meermeier et al., 2016 ). We used 128 face stimuli, taken from different databases, 70 from the Karolinska directed emotional faces database (KDEF; Lundqvist et al., 1998 ), 32 from the dataset collected at the European Conference on Visual Perception (ECVP) in Utrecht ( http://pics.stir.ac.uk/ ), 10 from the CVL database provided by the Computer Vision Laboratory, University of Ljubljana, Slovenia ( Peer et al., 2014 ), 16 from the Multi-Racial Mega-Resolution database (MR2; Strohminger et al., 2016 ). Images from each database contained the same amount of male and female faces, and all faces were shown from a frontal view with smiling or neutral expression.…”

The automaticity of semantic processing revisited: Auditory distraction by a categorical deviation.

“…The TBR sequences now comprised seven male faces taken without replacement and arranged in a random order. The face images from CVL Face Database used in this work have been provided by the Computer Vision Laboratory, University of Ljubljana, Slovenia (Peer, Emeršic ˇ, Bule, Žganec-Gros, & Štruc, 2014). Two sets of faces were generated.…”

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

“…To address this issue, we use a coarselevel pre-training to make the training starting at a good initial status. We collect 6,655 frontal face photos taken from ten face datasets [37,21,6,25,24,7,35,34,4,36]. For each photo, we generate a synthetic drawing using the twotone NPR algorithm in [27].…”