A Review on Automatic Marker Identification Methods in Watershed Algorithms Used for Medical Image Segmentation
Kumar Thirunellai Rajamani · 2015
Medical imaging is the process of representing human body parts with the help of modern electronic devices such as computer. Segmenting a region of interest (ROI) from the medical images is an important and challenging task for the clinicians. There are many algorithms are proposed for medical image segmentation. Watershed algorithm is a mathematical morphology based method and it can be effectively used for medical image segmentation applications. The main objective of watershed algorithm is to find watershed lines for separating the objects from its background. Because of the noises and other irregularities present in the image, watershed algorithm leads to a problem of over-segmentation. A solution to this problem is the use of internal and external markers for representing foreground and background regions respectively. There are many methods used for finding markers in the medical images. In this paper we present a review on various methods used for marker identification in medical images. This review also includes a small description about different medical imaging modalities, mathematical morphology method and watershed algorithm. For an experimental result, this paper also compares the segmentation accuracy of commonly used marker identification methods.