Implementation of a Distributed Watershed Algorithm

Moga, Alina N.; Viero, T.; Dobrin, Bogdan; Gabbouj, Moncef

doi:10.1007/978-94-011-1040-2_36

Cited by 17 publications

(16 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…had given some parallel methods of watershed transform based on definition by topographical distance [3]. We have learned from [4] that the proposed method based on Ordered Queue (OQ for short) is derived from optimal sequential watershed algorithm, but its scalability is quite limited. While an alternative solution, namely image integration by sequential scanning, introduced by [5], provides an equitable work load on multiprocessors, and hence a better relative speedup, but the absolute running time of this algorithm is very long.…”

Section: Related Workmentioning

confidence: 99%

Further Optimized Parallel Algorithm of Watershed Segmentation Based on Boundary Components Graph

Zhou

Yang

Tang

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.Watershed segmentation/transform is a classical method for image segmentation in gray scale mathematical morphology. Nevertheless watershed algorithm has strong recursive nature, so straightforward parallel one has a very low efficiency. Firstly, the advantages and disadvantages of some existing parallel algorithms are analyzed. Then, a Further Optimized Parallel Watershed Algorithm (FOPWA) is presented based on boundary components graph. As the experiments show, FOPWA optimizes both running time and relative speedup, and has more flexibility.

show abstract

Section: Related Workmentioning

confidence: 99%

Further Optimized Parallel Algorithm of Watershed Segmentation Based on Boundary Components Graph

Zhou

Yang

Tang

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Several trials have been previously made to boost the performance of the watershed transformation by parallelizing its operations [15] [16] [17] [18] [19]. However, the task is not trivial because the operation itself is sequential relying on the results of previous steps of region growth.…”

Section: Introductionmentioning

confidence: 99%

Depth-First-Search Based Region Merging for the Waterfall

Jun

2015

2015 11th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

Watershed transformation is a popular method to segment regions in an image. After being proposed in 70's, it has been evolved in various ways. However, the problem of over-segmentation still remains because the existing approaches are computationally expensive; they apply a waterfall technique to the result of the watershed transformation, merging similar regions. The merging requires navigating the graph representing regions and their neighboring relationship. In this paper, we propose to improve navigation and merging process by transforming the graph into a tree and using the depth-first-search. The proposed method was able to simplify the region merging process while producing similar results.

show abstract

“…[2,5,8,9] since for large images the complexity of the analysis entails fast parallel algorithms. Previous experiments of parallelization of watersheds [11,16] using the classical sequential algorithm based on an ordered queue [2,9] resulted in not too ecient implementations. The reason is the highly sequential nature of the approach itself.…”

Section: Introductionmentioning

confidence: 99%