Parallel Image Component Labeling With Watershed Transformation

The parallel watershed transformation used in grayscale image segmentation is reconsidered in this paper on the basis of the component labeling problem. The main idea is to break the sequentiality of the watershed transformation and to correctly delimit the extent of all connected components locally, on each processor, simultaneously. The internal fragmentation of the catchment basins, due to domain decomposition, into smaller subcomponents is ulteriorly solved by employing a global connected components operator. Therefore, in a pyramidal structure of master|slave processors, internal contours of adjacent subcomponents within the same component are hierarchically removed. Global nal connected areas are e ciently obtained in log2N steps on a logical grid of N processors. Timings and segmentation results of the algorithm built on top of the Message Passing Interface (MPI) and tested on the Cray T3D are brought forward to justify the superiority of the novel design solution compared against previous implementations. 1This research has been supported by the Graduate School in Electronics, Telecommunication and Automation (GETA), and Edinburgh Parallel Computing Centre in the Training and Research on Advanced Computing Systems (TRACS) programme. 1