Deep Learning and Neural Architectures for Face Recognition on Mobile Devices  Dr. Souad Khellat Kihel Biometric technologies are now widely used in personal mobile devices. The technological improvements in mobile computing platforms make it possible to embed resource-intensive processes such as human faces recognition. The more the cooperation of the user is limited, such as in the case of continuous authentication, the more is difficult to match human performances. The neural architectures and Deep learning has shown great efficiency in the last decade and this is mainly due to the computation between the image and the representation in the cortex area. We propose a biologically-inspired system to perform face recognition by processing image areas captured at different fixation points. An S1C1 architecture is proposed to extract the features from a facial region. In addition, we propose to visualize the representation space produced from a deep network. A biologically inspired architecture based on ocular parts and peripheral vision will be presented based on the fusion between the HMAX and the Log-Polar mapping. Finally, a prototype system based on facial emotion will be also highlighted.

Su segnalazione di

Massimo Tistarelli
Dipartimento di Agraria