Please refer to Massad et al. (1998a) and Massad et al. (1998b) for further details on a 3-D object recognition system based on the combination of viewer centred representations and temporal associations. The results achieved with this system show its capability to autonomously learn and to recognize considerably similar objects. Furthermore the given examples illustrate the benefits for object recognition stemming from the utilization of the temporal context. Ambiguous views become manageable and a higher degree of insensitiveness against misclassifications can be accomplished.