We propose a new active vision system that mimics a saccadic movement of hu
man eye. It is implemented based on a new computational model using neural
networks. In this model, the visual pathway was divided in order to categor
ize a saccadic eye movement into three parts. each of which was then indivi
dually modeled using different neural networks to reflect a principal funct
ionality of brain structures related with the saccadic eye movement in our
brain. Initially. the visual cortex for saccadic eye movements was modeled
using a self-organizing feature map, then a modified learning vector quanti
zation net work was applied to imitate the activity of the superior collicu
lus relative to a visual stimulus. In addition. a multilayer recurrent neur
al network, which is learned by an evolutionary computation algorithm, was
used to model the visual pathway from the superior colliculus to the oculom
otor neurons. Results from a computer simulation show that the proposed com
putational model is effective in mimicking the human eve movements during a
saccade. Based on the proposed model, an active vision system using a CCD
type camera and motor system was developed and demonstrated with experiment
al results.