The most important ability of the human vision is object recognition, yet it is exactly the less understood aspect of the vision system. Computational models have been helpful in progressing towards an explanation of this obscure cognitive ability, and today it is possible to conceive more refined models, thanks to the new availability of neuroscientific data about the human visual cortex. This work proposes a model of the development of the object recognition capability, under a different perspective with respect to the most common approaches, with a precise theoretical epistemology. It is assumed that the main processing functions involved in recognition are not genetically determined and hardwired in the neural circuits, but are the result of interactions between epigenetic influences and the basic neural plasticity mechanisms. The model is organized in modules related with the main visual biological areas, and is implemented mainly using the LISSOM architecture, a recent self-organizing algorithm closely reflecting the essential behavior of cortical circuits.