Abstract
Watershed is a widespread technique for image segmentation. Many researchers apply the method implemented in open source libraries without a deep understanding of its characteristics and limitations. In the review, we describe benchmarking outcomes of six open-source marker-controlled watershed implementations for the segmentation of 2D and 3D images. Even though the considered solutions are based on the same algorithm by flooding having O(n)computational complexity, these implementations have significantly different performance. In addition, building of watershed lines grows processing time. High memory consumption is one more bottleneck for dealing with huge volumetric images. Sometimes, the usage of more optimal software is capable of mitigating the issues with the long processing time and insufficient memory space. We assume parallel processing is capable of overcoming the current limitations. However, the development of concurrent approaches for the watershed segmentation remains a challenging problem.
Highlights
Segmentation of a digital image is the process of its division into a number of disjoint regions, so that pixels of every region have similar visual characteristics
One of most common segmentation algorithms used in processing medical [6,7] and material science images [8,9] is a watershed algorithm. It is based on the representation of a grayscale image as a topographic relief, flooded with water, where watersheds are lines dividing areas of the water from different basins [10]
On the basis of the experimental data, we plotted the dependence of the execution time on the images size: Figure 6 for images without the construction of watershed lines (WL) and Figure 7 with it
Summary
Segmentation of a digital image is the process of its division into a number of disjoint regions, so that pixels of every region have similar visual characteristics. The goal is to simplify or change the representation of an image for its further analysis. This is one of the most important tasks in pattern recognition and classification [1], visualization [2,3], image compression based on objects of interest [4,5], etc. One of most common segmentation algorithms used in processing medical [6,7] and material science images [8,9] is a watershed algorithm It is based on the representation of a grayscale image as a topographic relief, flooded with water, where watersheds are lines dividing areas of the water from different basins [10]. After its first proposal [11,12], this approach has developed significantly [13,14,15,16,17]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
