Study on adaptive segmentation of irregular image based on improved PCNN

• Graphics and image processing • Previous Articles Next Articles

Study on adaptive segmentation of irregular image based on improved PCNN

<a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=(((Deng-Chao Feng[Author]) AND 1[Journal]) AND year[Order])" target="_blank">Deng-Chao Feng</a> <a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=(((Zhao-Xuan Yang[Author]) AND 1[Journal]) AND year[Order])" target="_blank">Zhao-Xuan Yang</a> <a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=(((Zhe Wang[Author]) AND 1[Journal]) AND year[Order])" target="_blank">Zhe Wang</a> <a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=(((Pereira Jose Miguel[Author]) AND 1[Journal]) AND year[Order])" target="_blank">Pereira Jose Miguel</a>

Received:2007-11-05 Revised:1900-01-01 Online:2008-03-01 Published:2008-03-01
Contact: Deng-Chao Feng

基于改进型PCNN的不规则图像自适应分割算法研究

冯登超杨兆选王哲 J.M.Dias Pereira

天津大学天津大学太原理工大学 Escola Superior de Tecnologia doIPS, Rua do Vale de Chaves,Portugal

通讯作者: 冯登超

Abstract

Abstract: Concerning the characteristics of complex components of irregular images and random alignment of irregular spot without proper fitting mathematics model, an adaptive segmentation algorithm with improved Pulse Coupled Neural Network （PCNN） was proposed in the paper. On the basis of basic PCNN model, the neurons feedback input function and dynamic threshold function were modified and multi-level output model for the neuron output was designed to implement the segmentation process as well. Simulation experiment shows that the improved PCNN has better robustness and can realize the adaptive segmentation of irregular image.

Key words: irregular image, Pulse Coupled Neural Network （PCNN）, dynamic threshold, adaptive segmentation

摘要： 针对不规则图像成分复杂、特征形状无法采用经典模型拟合等问题，提出了基于改进型脉冲耦合神经网络（PCNN）的自适应分割算法。该算法在原有PCNN模型基础上，对神经元反馈输入函数和动态阈值函数进行了修正，同时对神经元的输出采用多级输出模型，从而实现对不规则图像的分割。仿真实验表明，改进后的算法能够实现不规则图像的自适应分割，鲁棒性较好。

关键词: 不规则图像；脉冲耦合神经网络；动态阈值；自适应分割

Deng-Chao Feng Zhao-Xuan Yang Zhe Wang Pereira Jose Miguel. Study on adaptive segmentation of irregular image based on improved PCNN[J]. Journal of Computer Applications.

冯登超杨兆选王哲 J.M.Dias Pereira. 基于改进型PCNN的不规则图像自适应分割算法研究[J]. 计算机应用.

[1]	Guangzhu XU, Wenjie LIN, Sha CHEN, Wan KUANG, Bangjun LEI, Jun ZHOU. Fundus vessel segmentation method based on U-Net and pulse coupled neural network with adaptive threshold [J]. Journal of Computer Applications, 2022, 42(3): 825-832.
[2]	YU Dunhui, YUAN Xu, ZHANG Wanshan, WANG Chenxu. Spatiotemporal crowdsourcing online task allocation algorithm based ondynamic threshold [J]. Journal of Computer Applications, 2020, 40(3): 658-664.
[3]	ZHANG Xingsheng, YU Dunhui, ZHANG Wanshan, WANG Chenxu. Time utility balanced online task assignment algorithm under spatial crowdsourcing environment [J]. Journal of Computer Applications, 2019, 39(5): 1357-1363.
[4]	LIU Dong, ZHOU Dongming, NIE Rencan, HOU Ruichao. Multi-focus image fusion based on phase congruency motivate pulse coupled neural network-based in NSCT domain [J]. Journal of Computer Applications, 2018, 38(10): 3006-3012.
[5]	GAO Yuan, JIA Ziting, QIN Pinle, WANG Lifang. Medical image fusion algorithm based on linking synaptic computation network [J]. Journal of Computer Applications, 2017, 37(12): 3554-3557.
[6]	CHENG Shuli, WANG Liejun, QIN Jiwei, DU Anyu. Image segmentation algorithm based on fusion of group intelligent algorithm optimized OTSU-entropy and pulse coupled neural network [J]. Journal of Computer Applications, 2017, 37(12): 3528-3535.
[7]	LIU Shangwang, LI Ming, HU Jianlan, CUI Yanmeng. Image classification method based on visual saliency detection [J]. Journal of Computer Applications, 2015, 35(9): 2629-2635.
[8]	YANG Dayong, YANG Jianhua, LU Wei. Foreground detection algorithm based on dynamic threshold kernel density estimation [J]. Journal of Computer Applications, 2015, 35(7): 2033-2038.
[9]	LU Yang, BAO Shudi, ZHOU Xiang, CHEN Jinheng. Real-time human identification algorithm based on dynamic electrocardiogram signals [J]. Journal of Computer Applications, 2015, 35(1): 262-264.
[10]	ZHENG Yan LU Ran ZHAO Ai-hua. Dynamic topic model amending method based on feedback stories [J]. Journal of Computer Applications, 2012, 32(05): 1343-1346.
[11]	CHENG Yuan-yuan LI Hai-yan CHEN Hai-tao SHI Xin-ling. Mixed noise filtering via limited grayscale pulse coupled neural network [J]. Journal of Computer Applications, 2012, 32(03): 729-731.
[12]	LI Hai-yan ZHANG Yu-feng SHI Xin-ling CHEN Jian-hua. Image segmentation based on grayscale iteration threshold pulse coupled neural network [J]. Journal of Computer Applications, 2011, 31(10): 2753-2756.
[13]	LI Jianfeng ZOU Beiji LI Lingzhi XIN Guojiang. Image identification method based on local time series of intersecting cortical model [J]. Journal of Computer Applications, 2011, 31(06): 1588-1591.
[14]	Hai-yan LI Yu-feng ZHANG Xin-ling SHI Jian-hua CHEN. Adaptive filtering method for images based on pulse-coupled neural network [J]. Journal of Computer Applications, 2011, 31(04): 1037-1039.
[15]	. Study on error diffusion algorithm of digital halftoning [J]. Journal of Computer Applications, 2010, 30(4): 925-928.