Analysis of results of large-scale multimodal biometric identity verification experiment

• Published in: IET biometrics Vol. 8; no. 1; pp. 92 - 100
• Main Authors: Czyżewski, Andrzej, Hoffmann, Piotr, Szczuko, Piotr, Kurowski, Adam, Lech, Michał, Szczodrak, Maciej
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.01.2019; John Wiley & Sons, Inc
• Subjects: Accuracy; bank branches; bank clients; bank tellers; banking tellers; biometric data; biometric modalities; Biometrics; biometrics (access control); Clients; consecutive identity verification attempts; Data acquisition; Data analysis; Data collection; Data mining; data mining process; Data processing; Datasets; experimental biometric system; identity verification attempt; identity verification methods; large‐scale multimodal biometric identity verification experiment; linguistic methods; Methods; multimodal dataset; Research Article; rough set theory; rough sets methodology; Sensors; Sentiment analysis; Software; studied biometric methods; subjective opinions; Verification; verification phase; verifications; identity verification attempt; data mining; bank clients; subjective opinions; banking tellers; biometrics (access control); verifications; bank branches; data mining process; biometric data; experimental biometric system; identity verification methods; linguistic methods; rough sets methodology; studied biometric methods; bank tellers; data acquisition; large-scale multimodal biometric identity verification experiment; consecutive identity verification attempts; rough set theory; verification phase; multimodal dataset; biometric modalities
• ISSN: 2047-4938; 2047-4946; 2047-4946
• DOI: 10.1049/iet-bmt.2018.5030

An analysis of a large set of biometric data obtained during the enrolment and the verification phase in an experimental biometric system installed in bank branches is presented. Subjective opinions of bank clients and of bank tellers were also surveyed concerning the studied biometric methods in order to discover and to explore relations emerging from the obtained multimodal dataset. First, data acquisition and identity verification methods are described in this study. Then, relationships between ratios of successful and failed verifications between pairs, triplets, and quartets of biometric modalities are studied. An analysis of the sentiment of clients and of banking tellers related to each identity verification attempt was performed based on linguistic methods. The data mining process is described, based on the rough sets methodology, aimed at deriving rules pertaining to consecutive identity verification attempts.