Near infrared sensing and associated landmark detection for face recognition

We present, in this work, a new system of Near-Infrared capture that aims to eliminate ambient light effects. We designed this sensor to be integrated into the mobile platform VINSI. One of the originalities of this sensor is that we can acquire two images at the same time: one in infrared and the other in visible light. We developed a novel method for landmark detection of sufficiently low complexity so that it can be implemented on our mobile platform. We tested this method on three different near-infrared face databases, and we observed stability in the results of localization precision over these databases associated to performance comparable to the state of the art.