Multi-object Segmentation Based on Improved Pulse Coupled Neural Network

Dansong Cheng,Xianglong Tang,Jiafeng Liu,Xiaofang Liu

doi:10.5539/cis.v1n4p91

Abstract

This paper introduces an approach for image segmentation by using pulse coupled neural network (PCNN), based on the phenomena of synchronous pulse bursts in the animal visual cortexes. The synchronous bursts of neurons with different input were generated in the proposed PCNN model to realize the multi-object segmentation. The criterion to automatically choose the dominant parameter (the linking strength ?), which determines the synchronous-burst stimulus range, was described in order to stimulate its application in automatic image segmentation. Segmentations on several types of image are implemented with the proposed method and the experimental results demonstrate its validity.

Highlights

The neuron receives input signals from other neurons and external sources by two channels in the receptive field
Feeding input is the intensity of the image pixel connected to neuron and received by channel F, see (1)
It can be seen that, to lowly noised image, the rate of false negative in improved pulse coupled neural network (PCNN) model is lower than traditional Fastlinking model

Summary

Introduction

The neuron receives input signals from other neurons and external sources by two channels in the receptive field. In figure 1, feeding input is the intensity of the image pixel connected to neuron and received by channel F, see (1). It is multiplied by the feeding input and the bias is taken to be unity, see (3). The input wave transmit the data after one iteration is finished, while linking territory wave send information to all the elements of image during this iterative. It can be seen from Figure[3] (b) and (c) that, for the connected territory, the value of β influences the amount of neurons

Methods

Conclusion