CAJ | 학술논문

提出了一种综合支持向量机(Support Vector Machine,SVM)和模板匹配的尿沉渣识别算法.首先根据面积特征将有形成分粗分成大目标类和小目标类,然后对小目标类中的草酸钙结晶以模板匹配法识别,而红、白细胞采用SVM的方法进行分类,最后对大目标类中的上皮细胞和管型则根据其狭长度加以区分.实验表明,该算法在将尿沉渣识别率提高到96.7%的同时还节约了22.4%的识别时间.
제출료일충종합지지향량궤(Support Vector Machine,SVM)화모판필배적뇨침사식별산법.수선근거면적특정장유형성분조분성대목표류화소목표류,연후대소목표류중적초산개결정이모판필배법식별,이홍、백세포채용SVM적방법진행분류,최후대대목표류중적상피세포화관형칙근거기협장도가이구분.실험표명,해산법재장뇨침사식별솔제고도96.7%적동시환절약료22.4%적식별시간.
An algorithm based on Support Vector Machine(SVM) and template matching is designed to classify the urinary sedi-ment.Firstly,visible compositions in urinary sediment are classified roughly into big object and small object following their area, the former includes epithelial cells and pipe type,the latter includes crystallization,leukocyte and erythrocyte.Secondly,the tem-plate matching method is used to identify the crystallization,and by constructing an optimal SVM classifier,leukocyte and erythro-cyte are different in the most extent.Finally,these big objects are classified into epithelial cells and pipe type following narrow extent.Exporiment shows that the proposed method not only can gain beuer recognition rate(96.7%),but also reduces 22.4% com-puting time.