%0 Generic %1 samangouei2016convolutional %A Samangouei, Pouya %A Chellappa, Rama %D 2016 %K cnn face %T Convolutional Neural Networks for Facial Attribute-based Active Authentication on Mobile Devices %U http://arxiv.org/abs/1604.08865 %X 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.

@misc{samangouei2016convolutional, 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.}, added-at = {2016-05-02T17:09:08.000+0200}, author = {Samangouei, Pouya and Chellappa, Rama}, biburl = {https://www.bibsonomy.org/bibtex/2c374913ad1a28d87c217bfe5b722ef21/ii}, description = {Convolutional Neural Networks for Facial Attribute-based Active Authentication on Mobile Devices}, interhash = {bb2c6a8678ba3c66e2ed92473fffe2cc}, intrahash = {c374913ad1a28d87c217bfe5b722ef21}, keywords = {cnn face}, note = {cite arxiv:1604.08865}, timestamp = {2016-05-02T17:09:08.000+0200}, title = {Convolutional Neural Networks for Facial Attribute-based Active Authentication on Mobile Devices}, url = {http://arxiv.org/abs/1604.08865}, year = 2016 }