|本期目录/Table of Contents|

[1]马跃辉,辛月兰.基于改进SPCNN的双阈值自适应分割[J].电子设计工程,2019,27(22):55-60.
 MA Yuehui,XIN Yuelan.A double threshold adaptive segmentation method based on SPCNN[J].SAMSON,2019,27(22):55-60.
点击复制

基于改进SPCNN的双阈值自适应分割(PDF)
分享到:

《电子设计工程》[ISSN:1674-6236/CN:61-1477/TN]

卷:
27
期数:
2019年22期
页码:
55-60
栏目:
计算机技术应用
出版日期:
2019-11-20

文章信息/Info

Title:
A double threshold adaptive segmentation method based on SPCNN
文章编号:
1674-6236(2019)22-0055-06
作者:
马跃辉辛月兰
(青海师范大学 物理与电子信息工程学院,青海 西宁 810000)
Author(s):
MA Yue?hui XIN Yue?lan
(College of Physics & Electronic Information Engineering,Qinghai Normal University,Xining 810000, China)
关键词:
脉冲耦合神经网络 图像分割 抗噪性 最大类间方差法
Keywords:
pulse coupled neural network image segmentation noise suppression OTSU
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
为解决脉冲耦合神经网络(Pulse Coupled Neural Network, PCNN)在图像分割中存在噪声适应性差、分割效率低等问题,提出一种基于SPCNN的双阈值自适应分割方法。首先通过整合拉普拉斯算子和高斯函数设计反馈输入域的连接系数矩阵,使图像在分割过程中在保护边缘细节的同时也具有抗噪性;然后利用最大类间方差法构造全新的双阈值点火判别模型,实现对目标像素的耦合点火。实验表明,该方法在实现参数自适应性的同时提高了分割效率,且具有良好的抗噪性。
Abstract:
To solve the problem of poor noise adaptability and low efficiency of Pulse Coupled Neural Network methods in image segmentation, a double threshold adaptive segmentation method based on SPCNN is proposed. First, the weight matrix of the feeding input field is designed by combined Laplace operator and Gauss function to protect the edge details and also have the noise resistance in the process of segmentation. Then, in order to realize the adaptability of parameter selection adopts the method of the orientation information measure. Last, put forward a new double threshold ignition discriminant model based on the method of maximum variance between classes to realize the adaptability of parameter selection. Experiments show that the proposed method improves the segmentation efficiency and achieves good noise immunity while achieving adaptive parameters.

参考文献/References:

[1] Rafael C. Gonzalez, Richard E. Woods. Digital image processing [M]. Publishing House of Electronics Industry, BEIJING, 2011:443-444.[2] DENG X, Ma Y. PCNN model analysis and its automatic parameters determination in image segmentation and edge detection[J]. Chinese Journal of Electronics, 2014, 23 (1):97-103.[3] 郭业才,周林峰.基于脉冲耦合和图像熵的各向异性扩散模型研究[J].物理学报,2015, 5(19):194204-1.[4] 唐士生, 陈绚青, 基于超模糊熵ULPCNN二值图像分割算法研究与实现[J].激光杂志,2016,37 (1):113-116.[5] Mario I, Chacon M, Jessica A. Time Series Classifier For Texture Segmentation[C]// Fuzzay Information Processing Society(NAFIPS): 2011 Annual Meeting of the North American,2011:1-6.[6] Lian J, Ma Y, Ma Y, Shi B. Automatic gallbladder and gallstone regions segmentation in ultrasound image[J]. Int J Comput Assist Radiol Surg, 2017, 12(4):1-16. [7] 吴俊, 孙明明,肖志涛. 联合蚁群算法和PCNN的脑部MRI图像分割方法[J]. 光电子激光:2014,25(3):614-619.[8] TAN W, ISA N A M. Segmentation and detection of human spermatozoa using modified Pulse Coupled Neural Network optimized by Particle Swarm Optimization with Mutual Information[C]//Proceedings of the 10th Conference on Industrial Electronics and Applications, IEEE,2014:192-197.[9] Rajeswari S, Josephine M S, Jeyabalaraja V. An elm predictive model for risk assessments of CVD in impaired glucose tolerance (IGT) patients via genpcnn and slfns algorithm[J]. Journal of Theoretical & Applied Information Technology, 2018,96(3):605-615.[10]He F,Guo Y,Gao C. An improved pulse coupled neural network with spectral residual for infrared pedestrian segmentation[J]. Infrared Physics & Technology, 2017(87):22-30.[11]Guo Z, Li X, Huang H, et al. Deep learning-based image segmentation on multi-modal medical imaging[J]. IEEE Transactions on Radiation and Plasma Medical Sciences, 2019,12(99):1-1.[12]贺付亮,郭永彩,高潮.复杂环境下用于人体目标红外图像分割的改进PCNN方法[J].光学学报,2017,2(2):0215003.[13]周东国,高潮,郭永彩. 一种参数自适应的简化PCNN图像分割方法[J]. 自动化学报,2014,6(40):1191-1197.[14]张新伟,易克川,高连兴. 基于脉冲耦合神经网络的黏连玉米种子图像分割[J]. 中国农业大学学报,2015,20(3):208-215.[15]朱俊锋,胡翔云,张祖勋.多尺度点云噪声检测的密度分析法[J].测绘学报,2015,3(44):282-291.[16]余金栋,张宪民.用于线纹显微图像的边缘检测算法[J].光学精密工程,2015,1(23):271-281.[17]Cai H, Yang Z, Cao X, et al, A new iterative triclass thresholding technique in image segmentation[J].IEEE Transaction on Image Processing,2014,23(3):1038-1046.[18]许芹,唐敦兵,蔡祺祥.改进的快速模糊C均值聚类图像分割算法[J].南京理工大学学报,2016,40(3):309-314.[19]袁小翠,吴禄愼,陈华伟.基于OTSU方法的钢轨图像分割[J].光学精密工程, 2016,7(24):1772-1781.[20]郑欣,彭真明.基于活跃度的脉冲耦合神经网络图像分割[J].光学精密工程,2013,3(3):821-827

相似文献/References:

[1]武 园,葛玉荣.一种基于脑部肿瘤MR图像的分割方法[J].电子设计工程,2014,(10):50.
 WU Yuan,GE Yu-rong.A method based on brian tumor MR image segmentation[J].SAMSON,2014,(22):50.
[2]孙东卫,赵 镭,杨振元. 基于最优阈值法的锅炉火焰图像处理的研究[J].电子设计工程,2013,(18):136.
 SUN Dong-wei,ZHAO Lei,YANG Zhen-yuan. Research on boiler flame image processing based on the optimal threshold method[J].SAMSON,2013,(22):136.
[3]晁 越,李中健,黄士飞. OpenCV图像处理编程研究[J].电子设计工程,2013,(10):175.
 CHAO Yue,LI Zhong-jian,HUANG Shi-fei. Programming and image processing based on the realization OpenCV[J].SAMSON,2013,(22):175.
[4]何维娜,张丽丽. 人工神经网络在金相图像分割中的应用研究[J].电子设计工程,2013,(03):143.
 HE Wei-na,ZHANG Li-li. Study on artificial neuronal networks applied on microstructure segmentation from metallographic images[J].SAMSON,2013,(22):143.
[5]杨修国. 基于遗传算法的最大类间方差法的改进[J].电子设计工程,2013,(01):188.
 YANG Xiu-gu. Genetic algorithm based on Otsu method improvement[J].SAMSON,2013,(22):188.
[6]杨修国. 浅谈图像阈值分割技术[J].电子设计工程,2012,(23):36.
 YANG Xiu-guo. Discussion of image threshold segmentation[J].SAMSON,2012,(22):36.
[7]赵艳妮,郭华磊,李敬华. 基于粒子群模糊C均值聚类的快速图像分割[J].电子设计工程,2012,(18):167.
 ZHAO Yan-ni,GUO Hua-lei,LI Jing-hua. Image segmentation based on particle swarm optimization fast fuzzy C-means clustering[J].SAMSON,2012,(22):167.
[8]杨修国. 关于直方图双峰法的研究与改进[J].电子设计工程,2012,(12 ):176.
 YANG Xiu-guo. Research and improvement on the histogram bimodal method[J].SAMSON,2012,(22):176.
[9]高俊钗1,韩 冰2.模糊目标轮廓图像分割研究[J].电子设计工程,2011,(13):170.
 GAO Jun-chai,HAN Bing.Image segmentation research on blurred object contour[J].SAMSON,2011,(22):170.
[10]张国权.基于遗传算法的彩色图像多阈值分割方法研究[J].电子设计工程,2011,(09):43.
 ZHANG Guo-quan.Study on multi-threshold segmentation for color image based on genetic algorithm[J].SAMSON,2011,(22):43.

备注/Memo

备注/Memo:
收稿日期:2019-03-14 稿件编号:201903109基金项目:国家自然科学基金资助项目(61662062);青海省自然科学基金项目(2016-ZJ-745)作者简介:马跃辉(1993—),男,山东临沂人,硕士研究生。研究方向:图像处理、计算机视觉。
更新日期/Last Update: 2019-11-22