Research on biometric recognition has long been focused on recognition from biometric data captured in ideal conditions. With recent advances in computer vision and machine learning the research focus shifted away from controlled laboratory conditions to unconstrained settings, where the variability of the captured biometric data is significantly higher and automatic recognition is a far more challenging task. Due to the countless deployment possibilities in security applications, surveillance, social media, consumer electronics or
border control, biometric recognition in unconstrained settings, nowadays often referred to as »biometrics in the wild«, increasingly attracts interest from universities, government agencies as well as private companies, and represents a highly active area of research.
The goal of this workshop is to present the most recent and advanced work related to biometric recognition in the wild and bring together researchers and practitioners working on problems related to unconstrained biometrics. Submitted papers should clearly demonstrate improvements over the existing state-of- the-art and use the most challenging datasets available. The workshop is interested in all parts of biometric systems ranging from detection/segmentation, landmark localization, pre-processing, and feature extraction techniques to modeling and classification approaches capable of operating on biometric data captured in the wild.