Segmentation of overlapping cervical nuclei based on the identification

查看全文 作　　者：Zhao [1]Jing;Xie [1]Yining;Lu [1]Yu;He [1]Yongjun 机构地区：[1]School of Computer Science and Technology,Harbin University of Science and Technology 出　　处：《The Journal of China Universities of Posts and Telecommunications》索引2018年第25卷第5期,共10页 基　　金：supported by the National Natural Science Foundation of China(61673142,61471145,61305001);the Foundation of Education Department of Heilongjiang Province(12511096);the Research Fund for the Doctoral Program of Higher Education of China(20132303120003);the Science Funds for the Young Innovative Talents of HUST(20152) 摘　　要：Image segmentation directly determines the performance of automatic screening technique. However,there are overlapping nuclei in nuclei images. It raises a challenge to nuclei segmentation. To solve the problem,a segmentation method of overlapping cervical nuclei based on the identification is proposed. This method consists of three stages: classifier training,recognition and fine segmentation. In the classifier training,feature selection and classifier selection are used to obtain a classifier with high recognition rate. In the recognition,the outputs of the rough segmentation are classified and processed according to their labels. In the fine segmentation,the severely overlapping nuclei are further segmented based on the prior knowledge provided by the recognition. Experiments show that this method can accurately segment overlapping nuclei. 关 键 词：图象分割 原子核 鉴定 分类器 识别率 屏蔽技术 分割方法 特征选择