Comparison of color thresholding and global thresholding for Ziehl-Neelsen TB bacilli slide images in sputum samples

Image segmentation is important in analysis of medical images. However, there are many constraints that must be faced such as variety of biological system and also limitation of mechine equipment. Thus, effective and precise method are needed to obtain correct diagnosis of quantitative medical samples. This paper studies the comparison between color thresholding and global thresholding techniques for segmenting Ziehl-Neelsen TB bacilli slide images in sputum samples. Color thresholding use RGB image as input while global thresholding used C-Y image as input. This technique has been tested onto 50 different images. The results obtained indicate that global thresholding method have better potential to ease next stage of image processing.