期刊
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
卷 107, 期 1, 页码 61-74出版社
ELSEVIER IRELAND LTD
DOI: 10.1016/j.cmpb.2011.10.004
关键词
Wireless capsule endoscopy; Ulcer; Colour-texture; Lacunarity; RGB HSV CIE Lab
Wireless capsule endoscopy (WCE) is a novel imaging technique that is gradually gaining ground as it enables the non-invasive and efficacious visualization of the digestive track, and especially the entire small bowel including its middle part. However, the task of reviewing the vast amount of images produced by a WCE examination is a burden for the physicians. To tackle this major drawback, an innovative scheme for discriminating endoscopic images related to one of the most common intestinal diseases, ulceration, is presented here. This new approach focuses on colour-texture features in order to investigate how the structure information of healthy and abnormal tissue is distributed on RGB, HSV and CIE Lab colour spaces. The WCE images are pre-processed using bidimensional ensemble empirical mode decomposition so as to facilitate differential lacunarity analysis to extract the texture patterns of normal and ulcerous regions. Experimental results demonstrated promising classification performance (mean accuracy >95%), exhibiting a high potential towards automatic WCE image analysis. (C) 2011 Elsevier Ireland Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据