Image Segmentation using Two-Layer Pulse Coupled Neural Network with Inhibitory Linking Field

Abstract

For over a decade, the Pulse Coupled Neural Network (PCNN) based algorithms have been used for image segmentation. Though there are several versions of the PCNN based image segmentation methods, almost all of them use singlelayer PCNN with excitatory linking inputs. There are four major issues associated with the single-burst PCNN which need attention. Often, the PCNN parameters including the linking coefficient are determined by trial and error. The segmentation accuracy of the single-layer PCNN is highly sensitive to the value of the linking coefficient. Finally, in the single-burst mode, neurons corresponding to background pixels do not participate in the segmentation process. This paper presents a new 2-layer network organization of PCNN in which excitatory and inhibitory linking inputs exist. The value of the linking coefficient and the threshold signal at which primary firing of neurons start are determined directly from the image statistics. Simulation results show that the new PCNN achieves significant improvement in the segmentation accuracy over the widely known Kuntimad’s single burst image segmentation approach. The two-layer PCNN based image segmentation method overcomes all three drawbacks of the single-layer PCNN.