一种优化脉冲耦合神经网络模型及在图像分割中的应用

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 215-217.

一种优化脉冲耦合神经网络模型及在图像分割中的应用

安琦,李敏,何玉杰,姚俊萍

第二炮兵工程大学西安710025;第二炮兵工程大学西安710025;第二炮兵工程大学西安710025;第二炮兵工程大学西安710025

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61102170)资助

Novel PCNN Model and its Application on Image Segmentation

AN Qi,LI Min,HE Yu-jie and YAO Jun-ping

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对目前脉冲耦合神经网络(PCNN)神经元模型参数主要通过人工设定问题,以简化参数为目的将PCNN模型的调制参数β与连接权矩阵K简化为链接系数矩阵W,提出一种优化PCNN神经元模型。该模型应用于图像分割时,充分利用图像本身空间和灰度特性自动确定链接系数,实现对图像的有效分割。实验结果表明,所提方法可以有效对图像进行自动分割,其分割效果优于Otsu方法、人工调整PCNN参数方法。

关键词: 优化PCNN模型,参数设定,图像自动分割中图法分类号TP183文献标识码A

Abstract: Considering the parameters of pulse coupled neural network (PCNN) are mainly adjusted manually,a novle PCNN model are proposed to reduce the parameters and simplifies its modulation parameter β and connect matrix K as linking matrix W.This paper brings forward a segmentation method based on a novel PCNN with the parameters determined by images’ spatial and grey characteristics automatically.Segmentations on images are implemented with the proposed method and the experimental result are better than that of other methods,such as Otsu method and manual adjustment method of PCNN parameters.

Key words: Novel PCNN model,Parameters determinations,Automatic image segmentation

安琦,李敏,何玉杰,姚俊萍. 一种优化脉冲耦合神经网络模型及在图像分割中的应用[J]. 计算机科学, 2014, 41(Z6): 215-217. https://doi.org/

AN Qi,LI Min,HE Yu-jie and YAO Jun-ping. Novel PCNN Model and its Application on Image Segmentation[J]. Computer Science, 2014, 41(Z6): 215-217. https://doi.org/

参考文献

[1] Eckhorn R,ReitBoeck H J,Arndt M,et al．Feature linking viasynchronization among distributed assemblies:simulation of results form cat visual cortex [J]．Nerual Computation,1990,2(3):293-307
[2] Johonson J L,Padgett M L．PCNN models and applications [J]．IEEE Transactions on Neural Networks,1999,10(3):480-498
[3] 李敏,蔡骋,谈正．基于修正PCNN的多传感器图像融合方法[J]．中国图像图形学报,2008,13(2):284-290
[4] 毕英伟,邱天爽.一种基于简化PCNN的自适应图像分割方法[J]．电子学报,2005,33(4):647-650
[5] Karvonen J A．Baltic sea ice SAR segmentation and classification using modified pulse coupled neural networks [J]．IEEE Transa-ctions on Geoscience and Remote Sensing,2004,42(7):1566-1574
[6] Chen Yu-li,Park S-K,Ma Yi-de,et al．A New Automatic Parame-ter Setting Method of a Simplified PCNN for Image Segmentation[J]．IEEE Transactions on Neural Networks,2011,22(6):880-892
[7] 赵峙江,赵春晖,张志宏．一种新的PCNN模型参数估算方法[J]．电子学报,2007,35(5):996-1000
[8] 于江波,陈后金,王巍,等．脉冲耦合神经网络在图像处理中的参数确定[J]．电子学报,2008(1):81-85
[9] 邓翔宇,马义德．PCNN参数自适应设定及其模型的改进[J]．电子学报,2012,40(5):955-964
[10] Wei Shuo,Hong Qu,Hou Meng-shu．Automatic image segmentation based on PCNN with adaptive threshold time constant[J]．Neuro computing,2011,74(9):1485-1491
[11] Berg H,Olsson R,Lindblad T,et al．Automatic design ofpulse coupled neurons for image segmentation[J]．Neuro Computing,2008,71(10-12):1980-1993
[12] 苗启广,王宝树．一种自适应PCNN多聚焦图像融合新方法 [J]．电子与信息学报,2006,28(3):466-470

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed