Automatic glasses detection is a hot topic
withing the large-scale face images classification domain,
which has impact on face recognition or soft biometrics for
person identification. In many practical video surveillance
applications, the faces acquired by cameras are low resolution.
Therefore, this type of applications requires processing
of a large number of relatively small-sized images. However,
continuous stream of image and video data processing is a
big data challenge. This need fits with the goals of Big Data
streaming processing systems. In this paper, we propose a
real-time Big Data architecture in order to collect, maintain
and analyze massive volumes of images related with the
problem of automatic glasses detection. This architecture
can be used as an automatic image tagging related with
glasses detection on face images.