Optimal parallel watershed algorithm based on image integration and sequential scannings

Watershed transformation is a tool for image segmentation widely used in computer vision applications. However, the complexity of processing large images entails fast parallel algorithms. In this paper, an improved SPMD (single program multiple data) watershed algorithm based on image integration and sequential scannings is rendered. The task performed by the algorithm is an alternative to the classical simulated immersion for computing the watershed image. Although the technique converges slow on a single processor computer, due to the repeated raster and anti-raster scannings of the image, it performs much faster in parallel, when subimages of the global image are simultaneously processed. Additionally, a global connected components operation employed for the parallel labeling of the seeds for region growing increases the efficiency of the algorithm. Results of a message passing interface (MPI) implementation tested on a Cray T3D parallel computer demonstrate the resilience of the presented parallel design solution to increasing number of processors, as to larger image sizes. ©2005 Copyright SPIE - The International Society for Optical Engineering