In this paper, we investigate the feasibility of building a visual memory for robotics spatial cognition without saving visual information. The proposed approach captures some properties of primate brain and especially the view cells. Our bio-inspired visual memory for cognitive map building consists of two main parts. One part is visual information extraction and the other part is the visual memory building using the Fuzzy Art architecture. The results of the current study could contribute to the development of bio-inspired model for cognitive map building which enables the mobile robot to localize itself and build a cognitive representation of its environment simultaneously like primates and humans.