Open AccessQUIS‐CAMPI: an annotated multi‐biometrics data feed from surveillance scenarios
Author(s) -
Neves João,
Moreno Juan,
Proença Hugo
Publication year - 2018
Publication title -
iet biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 28
eISSN - 2047-4946
pISSN - 2047-4938
DOI - 10.1049/iet-bmt.2016.0178
Subject(s) - benchmarking , biometrics , computer science , set (abstract data type) , data set , data quality , data mining , quality (philosophy) , artificial intelligence , metric (unit) , philosophy , operations management , epistemology , marketing , economics , business , programming language
The accuracy of biometric recognition in unconstrained scenarios has been a major concern for a large number of researchers. Despite such efforts, no system can recognise in a fully automated manner human beings in totally wild conditions such as in surveillance environments. Several sets of degraded data have been made available to the research community, where the reported performance by state‐of‐the‐art algorithms is already saturated, suggesting that these sets do not reflect faithfully the conditions in such hard settings. To this end, the authors introduce the QUIS‐CAMPI data feed, comprising samples automatically acquired by an outdoor visual surveillance system, with subjects on‐the‐move and at‐a‐distance (up to 50 m). Also, they supply a high‐quality set of enrolment data. When compared to similar data sources, the major novelties of QUIS‐CAMPI are: (i) biometric samples are acquired in a fully automatic way; (ii) it is an open dataset, i.e. the number of probe images and enroled subjects grow on a daily basis; and (iii) it contains multi‐biometric traits. The ensemble properties of QUIS‐CAMPI ensure that the data span a representative set of covariate factors of real‐world scenarios, making it a valuable tool for developing and benchmarking biometric recognition algorithms capable of working in unconstrained scenarios.