Visual Selection with Feature Contrast-Based Inhibition in a Network of Integrate and Fire Neurons

In this paper a visual selection mechanism based on an integrate and fire neural network is proposed for selecting objects in a given visual scene. In comparison to other visual selection approaches, our model is able to capture attention of objects in complex forms, including those linearly non-separable, and also processes a combination of features of an input scene, such as intensity, color and orientation. Moreover, computer simulations show that the model produce results similar to those observed in natural vision systems.