Contextual priming for artificial visual perception
Hervé Guillaume, Nathalie Denquive, Philippe Tarroux · 2005
Abstract – The construction of robotics autonomous systems able to identify objects in their environments requires the elaboration of efficient visual object recognition algorithms. Our knowledge of the mechanisms of natural perception suggests that, when the recognition process fails due to the degradation of the observation conditions and to the blurring of the intrinsic attributes of the objects, the information concerning the context is used by human for object recognition priming. In this case the indices used for object identification can be greatly simplified. We present in this paper an attempt to precise how such a principle can be applied to autonomous robotics. We show that using a compact frequency coding of the scene together with an unsupervised SOM learning we obtain syntactic categories that exhibit specific relationships with object categories. Thus, the construction of these syntactic categories should be useful for estimating the occurrence probability of object categories during the exploration of the perceptual space of a robotic system. 1.