Abstract
We present Deep Convolutional Neural Network (DCNN) architectures for the
task of continuous authentication on mobile devices by learning intermediate
features to reduce the complexity of the networks. The intermediate features
for face images are attributes like gender, and hair color. We present a
multi-task, part-based DCNN architecture for attributes detection are better
than or comparable to state-of-the-art methods in terms of accuracy. As a
byproduct of the proposed architecture, we explore the embedding space of the
attributes extracted from different facial parts, such as mouth and eyes. We
show that it is possible to discover new attributes by performing subspace
clustering of the embedded features. Furthermore, through extensive
experimentation, we show that the attribute features extracted by our method
performs better than previously attribute-based authentication method and the
baseline LBP method. Lastly, we deploy our architecture on a mobile device and
demonstrate the effectiveness of the proposed method.
Users
Please
log in to take part in the discussion (add own reviews or comments).