期刊名称：International Journal of Soft Computing & Engineering
电子版ISSN：2231-2307
出版年度：2013
卷号：3
期号：4
页码：47-51
出版社：International Journal of Soft Computing & Engineering
摘要：Tuberculosis (TB) is one of the major diseases in developing countries. TB detection is based on sputum examination microscopically by using Ziehl-Neelsen stain (ZN-stain) method, which is used worldwide. This method needs human expertise and intensive examination. The availability of expertise, time and cost are the constraints of the human intervention based examinations. Therefore, there is a need of automation of examin ation and detection of TB bacteria using digital image of ZN-stain sample. In this work, an algorithm based on image processing is developed for identification of TB bacteria in sputum. The method is based on Otsu thresholding and k-means clustering approach. The performance of clustering and thresholding algorithms for segmenting TB bacilli in tissue sections is compared. The developed automated technique shows good accuracy and efficiency.
