Tuberculosis is one of the deadly diseases worldwide
Tuberculosis is one of the deadly diseases worldwide, especially in developing countries including Ethiopia. It is caused by Mycobacterium tuberculosis that influenced fundamentally on human body lung in form of pulmonary tuberculosis disease. It also, detects based on sputum smear microscopy images examination at early stage diagnosis by using Ziehl-Neelsen (ZN) stained methods. Sputum smear microscopy is the most widely used diagnostic tools in developing countries. Therefore, there is need to develop automatic detection system for pulmonary tuberculosis by identifying causing bacilli from sputum smear microscopy images by using image processing techniques. In this study, an algorithm based on image processing technique is developed for identification pulmonary tuberculosis bacilli in digital image of stained sputum smear. The techniques was used in this study, for image preprocessing was used Gaussian filter to remove noise, contrast enhanced to enhance the quality of image and K-mean cluster used to separate image into region in image segment process. In addition, SVM is to identify bacilli, which classified the computed based on combined both morphological and color features from sputum smear images in two classes are bacilli detect and non-bacilli detect. The accuracy, sensitivity and specificity measure improved the performance of the prototype results are 94.4%, 95% and 94% respectively. The developed automatic detection system is shows good accuracy and efficiency used to assists the pathologists in making decision at early stage diagnosis of pulmonary tuberculosis.
