This paper proposed an improved selective attention model, which was designed as a network of spiking neurons of Hodgkin-Huxley type with star-like connections between the central units and peripheral neurons. In this model, peripheral neurons represent the neurons located in the primary visual cortex. Since orientation preference is an important property of neurons in primary visual cortex, it should be considered except for external stimuli intensity. Simulation results show that the improved model can sequentially select objects with different orientation preferences and have a reliable shift of attention from one object to another, which are consistent with the experimental results that the neurons with different orientation preferences are laid out in pinwheel patterns.