Parallel Image Segmentation Using Reduction-Sweeps On Multicore Processors and GPUs

In this paper we introduce the Reduction Sweep algorithm, a novel graph-based image segmentation algorithm that is designed for easy parallelization. It is based on a clustering approach focusing on local image characteristics. Each pixel is compared with its neighbors in an implicitly independent manner, and those deemed sufficiently similar according to a color criterion are joined. We achieve fast execution times while still maintaining the visual quality of the results. The algorithm is presented in four different implementations: sequential CPU, parallel CPU, GPU, and hybrid CPU-GPU. We compare the execution times of the four versions with each other and with other closely related image segmentation algorithms.

@InProceedings { FFMC13,
  author       = "Farias, Renato and Farias, Ricardo and Marroquim, Ricardo and Clua, Esteban",
  title        = "Parallel Image Segmentation Using Reduction-Sweeps On Multicore Processors and GPUs",
  booktitle    = "2013 XXVI Conference on Graphics, Patterns and Image",
  pages        = "139--146",
  year         = "2013",
  note         = "http://dx.doi.org/10.1109/SIBGRAPI.2013.28",
  url          = "http://graphics.tudelft.nl/Publications-new/2013/FFMC13"
}