基于组合核支持向量机的图像边缘检测  

Edge detection based on linear combination of kernel function support vector machine

作　　者：张文娟[1] 贺兴时[1] 

机构地区：[1]西安工程大学理学院,西安710048

出　　处：《齐齐哈尔大学学报（自然科学版）》2010年第4期50-52,共3页Journal of Qiqihar University(Natural Science Edition)

摘　　要：基于支持向量机在分类上有很好的效果,提出了一种新的边缘检测方法--基于组合核支持向量机的图像边缘检测。该方法利用支持向量机分类对较多的训练样本数据进行训练,从而实现了图像边缘定位。通过实验验证了该方法比传统的边缘检测算子效果好。Based on the support vector machines possesses the outstanding performance of classification,this paper presents a new kernel function--linear combination kernel function support vector machines.The method of using support vector machine classification of the training sample data,so as to realize the training of image edge localization.The result of experiment shows that the support vector machines performance by using mixtures of kernels is much better than other traditional methods.

关 键 词：支持向量机 边缘检测 组合核函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]