Simplification of Mycobacterium Tuberculosis Segmenting Algorithm in Sputum Images Based of Auto-Thresholding

In medical image analysis, the most important thing is image segmentation, which is still a critical and important task until now. One application is in calculating the number of bacteria from the image of acid-resistant bacilli smear. A serious problem of segmentation algorithms that have been studied in sputum culture, is the problem of determining the number of bacteria. This paper provide automatic algorithm for Mycobacterium tuberculosis detection from the image of acid-fast bacilli smear, by using auto-thresholding segmentation method. This method could minimize calculation error during bacterial counting. Moreover, this method is the simple, fast and effective algorithm for bacterial counting.