计算机应用研究2012，Vol.29Issue(6)：2393-2396,2400,5.DOI:10.3969/j.issn.1001-3695.2012.06.106
胶囊内窥镜冗余图像数据自动筛除方法
Unsupervised redundant image deletion for wireless capsule endoscopy examination
摘要
Abstract
This paper proposed an unsupervised algorithm to delete the redundant WCE images, which was based on the analysis of the nurmalized mutual information and normalized cross-correlation coefficient between the successive frames. The algorithm firstly conducted quantification and clustering in HSV color space. Then, it calculated the similarity metrics between the successive frames. Finally, it iteratively applied deletion procedure according to the prescribed deletion rate. The pathology retaining rate, which was defined as the percentage of the remaining images bean tig pathological changes from the total ones was almost 100% with very low mis-deletion rate for 70% prescribed deletion rate of 49 patients. Experimental results show that the method baaed on the analysis of the normalized mutual information is effective to delete redundancy images and greatly reduces diagnosis time.关键词
胶囊内窥镜/归一化互信息量/归一化互相关系数/病灶数量保留率/图像误删率Key words
wireless capsule endoscopy( WCE)/normalized mutual information/normalized cross-correlation coefficient/pathology retaining rate/mis-deletion rate分类
信息技术与安全科学引用本文复制引用
孙宇千,吕庆文,刘哲星,刘思德..胶囊内窥镜冗余图像数据自动筛除方法[J].计算机应用研究,2012,29(6):2393-2396,2400,5.基金项目
广东省科技计划项目(2007B031302008,2009B010800019) （2007B031302008,2009B010800019）
广东省教育部产学研结合项目(2008 B090500200,2010B090400543) （2008 B090500200,2010B090400543）
科技部"科技人员服务企业行动"项目(2009GJE0047) （2009GJE0047）
