PROJECT TITLE :

PDE Based Algorithms for Smooth Watersheds

ABSTRACT:

Watershed segmentation is helpful for a variety of image segmentation problems with a wide selection of practical applications. Historically, the tracking of the immersion front is finished by applying a quick sorting algorithm. During this work, we have a tendency to explore a continuous approach primarily based on a geometric description of the immersion front which offers rise to a partial differential equation. The main advantage of employing a partial differential equation to track the immersion front is that the strategy becomes versatile and might easily be stabilized by introducing regularization terms. Coupling the geometric approach with a proper “merging strategy” creates a robust algorithm that minimizes over- and underneath-segmentation even without predefined markers. Since reliable markers outlined previous to segmentation will be troublesome to construct automatically for varied reasons, being able to treat marker-free situations could be a major advantage of the proposed method over earlier watershed formulations. The motivation for the ways developed during this paper is taken from high-throughput screening of cells. A absolutely automated segmentation of single cells permits the extraction of cell properties from massive information sets, which can give substantial insight into a biological model system. Applying smoothing to the boundaries can improve the accuracy in many image analysis tasks requiring an exact delineation of the plasma membrane of the cell. The proposed segmentation methodology is applied to real images containing fluorescently labeled cells, and the experimental results show that our implementation is sturdy and reliable for a selection of difficult segmentation tasks.