User Identification: Bio-Inspired Visual User Detection

This paper describes the bio-inspired visual detection for the smart user experience based on neuromorphic system, mimicking the visual cortex. The neuromorphic system is investigated for visual detection of users and their reaction, based on the VLSI neurons and synapses by CMOS conductance and Hodgkin-Huxley formalism. The proposed neuromorphic system exhibits the biologically plausible intelligent function mimicking the cat’s visual cortex experimentation of Hubel and Wiesel. The feasibility of bio-inspired vision is evaluated by visual detection of human head or pose under the limited natural environment. The visual detection in various environments of on-vehicle, glossy indoors, or dark conference room demonstrates as smart user interface to extend the internet service to IPTV as the smart phone of high user acceptance smart phone, with the robust function applicable to enhance the secure operation.