Application of Watershed Segmentation on Biomedical Images as an Educational Tool

Authors : Şefika Çağlan, Ali Değirmenci, İlyas Çankaya, Ömer Faruk Göktaş
Pages : 763-780
Doi:10.35234/fumbd.1706496
View : 31 | Download : 36
Publication Date : 2025-09-30
Article Type : Research Paper
Abstract :Image segmentation is the operation of dividing an image into multiple segments. Watershed segmentation is a widely used region-based segmentation method because of basic and fast features. This segmentation method that is based on morphological operations is used for several areas especially in medical image applications such as magnetic resonance imaging (MRI), computed tomography (CT) and histopathological images. In general, the segmentation problems with these types of images are originated from noise, nonhomogeneity and touching objects. For solving such problems, watershed segmentation is a powerful tool. In addition to all these advantages, if watershed segmentation is applied to image without any additional process, generally it gives an oversegmentation problem. Marker controlled watershed segmentation is improved to overcome this problem. In this article, five different algorithms about marker-controlled watershed segmentation, which each one is modified from five different articles, are applied on a grayscale bone plasmacytoma image and results are compared. An educational platform related with these algorithms is presented by using MATLAB App Designer. Designed graphical user interface (GUI) using App Designer is helpful tool for comparing different algorithms of marker-controlled watershed segmentation. Moreover, image processing learners can use it easily and can observe effectiveness of algorithms. So, the created educational platform has academic and educational characteristics. The advantage of this application is not only comparing different algorithms but also learning different marker-controlled watershed segmentation methods.
Keywords : Görüntü işleme, matematiksel morfoloji, segmentasyon, havza dönüşümü, MATLAB GUI

ORIGINAL ARTICLE URL