| Abstract | Face recognition in video is an example of the problem which is outstandingly well performed by humans, compared to the performance of machine-built recognition systems. This phenomenon is generally attributed to the following three main factors pertaining to the way human brain processes and memorizes information, which can be succinctly labeled as 1) non-linear processing, 2) massively distributed collective decision making, and 3) synaptic plasticity. Over the last half a century, many mathematical models have been developed to simulate these factors in computer systems.This presentation formalizes the recognition process, as it is performed in brain, using one of such mathematical models, within which the projection learning appears to be a natural improvement to the correlation learning. We show that, just as the correlation learning, the projection learning can also be written in incremental form. By taking in account the past data and being non-local, this rule however provides a way to automatically emphasize more important attributes and training data over the less important ones. The presented model, while providing a simple way to incorporate the main three factors of biological memorization listed above, is very powerful. This is demonstrated by incorporating it into a face recognition system which is shown to be capable of recognizing faces in video under conditions known to be very difficult for traditional Von-Neumann-type recognition systems. |
|---|
