[1]陈沅涛,徐蔚鸿,吴佳英,等.基于增量学习向量SVM方法的图像分割应用[J].南京理工大学学报(自然科学版),2014,38(01):6-11.
 Chen Yuantao,Xu Weihong,Wu Jiaying,et al.Image segmentation application based on incremental learning vector SVM algorithm[J].Journal of Nanjing University of Science and Technology,2014,38(01):6-11.
点击复制

基于增量学习向量SVM方法的图像分割应用
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
38卷
期数:
2014年01期
页码:
6-11
栏目:
出版日期:
2014-02-28

文章信息/Info

Title:
Image segmentation application based on incremental learning vector SVM algorithm
作者:
陈沅涛12徐蔚鸿12吴佳英12胡 蓉1
1.南京理工大学 计算机科学与工程学院,江苏 南京 210094; 2.长沙理工大学 计算机与通信工程学院,湖南 长沙 410014
Author(s):
Chen Yuantao12Xu Weihong12Wu Jiaying12Hu Rong1
1.School of Computer Science and Engineering,NUST,Nanjing 210094,China; 2.School of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410014,China
关键词:
支持向量机 增量学习向量支持向量机 图像分割 精简缩小集
Keywords:
support vector machine incremental learning vector support vector machine image segmentation thin narrow set
分类号:
TP391
摘要:
为了解决经典支持向量机方法已发现的执行时间长、执行效率低的相关问题,提出基于增量学习向量的支持向量机学习方法。该算法通过对训练样本集合的相关增量学习向量进行训练学习来得到初始支持向量机分类器。利用该初始化分类器在有关条件下针对初始训练样本集进行缩减得到精简缩小集,再应用精简缩小集针对初始支持向量机的分类器反向加工来得到支持向量机的最终分类器。该算法可大幅度降低大容量数据集上支持向量机的学习时间,并且具有很好的泛化能力。为了验证本学习方法的可应用性,从Berkeley图像分割数据集BSDS500和互联网上选取相关彩色图像进行仿真实验。该文实验结果表明:该方法得到分割结果的过程不仅比传统支持向量机耗时少,且与Berkeley图像分割数据集中人工标注结果比较得到较好分割效果。
Abstract:
In order to solve less efficient,longer time-consuming problem of the traditional SVM methods,this paper proposes a support vector machine learning algorithm based on the incremental vector.The algorithm obtains the initial support vector machine classifier by training the sample collection incremental vector learning.This paper streamlines the relevant conditions for initial training sample set to be streamlined narrow set by using the initialization classification,applies the thin narrow set of initial support vector machine classifier in reverse processing,and gets the support vector machine classification devices.The algorithm can significantly reduce the training time of support vector machine and large-capacity data set and has good generalization performance.In order to verify the application of the algorithm,this paper selects relative color images from Berkeley image segmentation data set BSDS500 and Internet experiments to do simulation experiment.The experimental results show that this segmentation process has much less time-consuming than the traditional support vector machine and better segmentation than the manually marked results in Berkeley image segmentation dataset.

参考文献/References:

[1] Platt J C.Fast training of SVMs using sequential minimal optimization[A].Advances in Kernel MethodsSupport Vector Learning[C].Scholkopf B,Burges C J C,Smola A J,1998:185-208.
[2]Keerthi S,Shevade S,Bhattacharyya C,et al.Improvements to platt's SMO algorithm for SVM classifier design[J].Neural Networks,1999,6(12):783-789.
[3]Zhang Ling,Zhang Bo.A geometrical representation of McCulloch-Pitts neural model and its applications[J].IEEE Transactions on Neural Networks,1999,10(4):925-929.
[4]Todorovic S,Nechyba M.Dynamic trees for unsupervised segmentation and matching of image regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1762-1777.
[5]Jiang Zhuolin,Lin Zhe,Davis L S.Label consistent K-SVD:Learning a discriminative dictionary for recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(11):2651-2664.
[6]Badrinarayanan V,Budvytis I,Cipolla R.Semi-supervised video segmentation using tree structured graphical models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(11):2751-2764.
[7]李红莲,王春花,袁保宗,等.针对大规模训练集的支持向量机的学习策略[J].计算机学报,2004,27(5):715-719.
Li Honglian,Wang Chunhua,Yuan Baozong,et al.A learning strategy of SVM used to large training set[J].Chinese Journal of Computers,2004,27(5):715-719.
[8]Canu S,Grandvalet Y,Guigue V,et al.SVM and kernel methods matlab toolbox[EB/OL].http://asi.insa-rouen.fr/~arakotom/toolbox/.2005-12-20.
[9]Arbelaez P,Maire M,Fowlkes C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):898-916.
[10]张培林,钱林方,曹建军,等.基于蚁群算法的支持向量机参数优化[J].南京理工大学学报,2009,33(4):464-468.
Zhang Peilin,Qian Linfang,Cao Jianjun,et al.Parameter optimization of support vector machine based on ant colony optimization algorithm[J].Journal of Nanjing University of Science and Technology,2009,33(4):464-468.
[11]李敏,罗洪艳,郑小林,等.一种改进的最大类间方差图像分割法[J].南京理工大学学报,2012,36(2):332-337.
Li Min,Luo Hongyan,Zheng Xiaolin,et al.Image segmentation based on improved Otsu algorithm[J].Journal of Nanjing University of Science and Technology,2012,36(2):332-337.

相似文献/References:

[1]周晓剑,马义中,刘利平,等.基于梯度信息的最小二乘支持向量回归机[J].南京理工大学学报(自然科学版),2011,(01):138.
 ZHOU Xiao-jian,MA Yi-zhong,LIU Li-ping,et al.Gradient-enhanced Least Squares Support Vector Regression[J].Journal of Nanjing University of Science and Technology,2011,(01):138.
[2]陈沅涛,徐蔚鸿,吴佳英.一种增量向量支持向量机学习算法[J].南京理工大学学报(自然科学版),2012,36(05):873.
 CHEN Yuan-tao,XU Wei-hong,WU Jia-ying.Incremental Vector Support Vector Machine Learning Algorithm[J].Journal of Nanjing University of Science and Technology,2012,36(01):873.
[3]杨赛,赵春霞.基于空间概率乘积核函数的图像分类算法[J].南京理工大学学报(自然科学版),2014,38(03):325.
 Yang Sai,Zhao Chunxia.Image classification algorithm based on spatial probability product kernel[J].Journal of Nanjing University of Science and Technology,2014,38(01):325.
[4]赵 莉.基于支持向量机的云计算资源负载预测模型[J].南京理工大学学报(自然科学版),2018,42(06):687.[doi:10.14177/j.cnki.32-1397n.2018.42.06.008]
 Zhao Li.Load forecasting model of cloud computing resourcesbased on support vector machine[J].Journal of Nanjing University of Science and Technology,2018,42(01):687.[doi:10.14177/j.cnki.32-1397n.2018.42.06.008]

备注/Memo

备注/Memo:
收稿日期:2012-09-08 修回日期:2013-06-18
基金项目:教育部重点科研项目(208098); 湖南省教育厅科研青年项目(12B005); 湖南省科技计划项目(2012FJ3005; 2012GK3056; 2012SK4046); 湖南省大学生研究性学习和创新性实验计划基金资助项目(湘教通[2013]191号501); 湖南省教育厅教研教改项目(ZJB2012061)
作者简介:陈沅涛(1980-),男,博士生,讲师,主要研究方向:模式识别与图像处理,E-mail:yufeng8552@qq.com。
引文格式:陈沅涛,徐蔚鸿,吴佳英,等.基于增量学习向量SVM方法的图像分割应用[J].南京理工大学学报,2014,38(1):6-11.
投稿网址:http://njlgdxxb.paperonce.org
更新日期/Last Update: 2014-02-28