CAJ | 학술논문

支持向量机方法在解决小样本,非线性及高维模式识别中表现出许多特有的优势。目前主要用于二元分类问题中,而对于其在多类分类应用仍是一个值得研究的问题。在目前存在的各种多类支持向量机分类问题中,一对一方法是一种最符合实际的方法。文章提出了一种改进的支持向量机,并将其应用于图像分割。这种改进的支持向量机它对一对一方法进行了改进,实验表明,支持向量机的方法是一种很有潜力的图像分割技术。
지지향량궤방법재해결소양본,비선성급고유모식식별중표현출허다특유적우세。목전주요용우이원분류문제중,이대우기재다류분류응용잉시일개치득연구적문제。재목전존재적각충다류지지향량궤분류문제중,일대일방법시일충최부합실제적방법。문장제출료일충개진적지지향량궤,병장기응용우도상분할。저충개진적지지향량궤타대일대일방법진행료개진,실험표명,지지향량궤적방법시일충흔유잠력적도상분할기술。
Support vector machine is a statistical theory based on the new machine learning method;it addresses the Small Sample, Non- linear and High Dimensional Pattern Recognition performance of the many unique advantages. At present it is mainly used for binary classification problems,and for its application in multi-class classification is still a problem worthy of study. In a variety of existing multi -class support vector machine classification problem, one-against-one is one of the most realistic approaches. This paper presents an improved support vector machines and applied it to image segmentation. This improved method of support vector machines is one of the improvements of one-against - one, experiments show that support vector machine approach is a promising image segmentation tech- nique.