Evaluation of Face Recognition Technologies for Access Authentication in Automotive Passive Entry Systems with Near Infrared Camera

Mauricio Vianna Rezende

Resumo


The development of embedded systems technology has changed the history of automotive world, bringing new devices including modern access vehicle’s control. In these systems’ recent history, industry has introduced the concept of Passive Access or Passive Entry (PASE) system, allowing the user to control vehicle’s doors opening and closing without the need for pressing any button. These systems are based on radio frequency devices with exchange of encrypted information with the Remote control Key (RKE), which assures user’s authentication. In spite of the comfort provided by this technology, there is the possibility of attacks against PASE and RKE authentication, exploring access security flaws, thus requiring constant research and development and improvement on these devices. This work proposes Face Recognition (FR) for user authentication integrated with PASE under unconstrained environments and illumination variation. The methodology was based on Design Science Research to support a FR novel implementation with the objective of evaluating system performance with Receiver Operating Characteristic (ROC) curves. A vehicle prototype already mounted with PASE system will integrate FR algorithms instantiations as artifacts: Eingenfaces, 2DFLD and Viola-Jones  detector, supported by Near Infrared Cameras (NIR). The results will be evaluated regarding computational cost (memory and processing time) of selected Face Recognition algorithms authentication. These results will be compared with available integrative capacity of automotive embedded devices.


Texto completo:

PDF (English)

Apontamentos

  • Não há apontamentos.




Projetos, Dissertações e Teses em Sistemas de Informação e Gestão do Conhecimento
ISSN 2358-5501 (Online)