Parallelization of a color-entropy preprocessed Chan-Vese model for face contour detection on multi-core CPU and GPU

@article{Shi2015ParallelizationOA,
  title={Parallelization of a color-entropy preprocessed Chan-Vese model for face contour detection on multi-core CPU and GPU},
  author={Xiaohua Shi and Fredrick Park and Lina Wang and Jack Xin and Yingyong Qi},
  journal={Parallel Computing},
  year={2015},
  volume={49},
  pages={28-49}
}
We introduce a novel way to parallelize a face contour detecting application.We develop a novel approach to parallelize the data-dependent core parts.We implement it on OpenCL for both multi-core CPU and GPU. Face tracking is an important computer vision technology that has been widely adopted in many areas, from cell phone applications to industry robots. In this paper, we introduce a novel way to parallelize a face contour detecting application based on the color-entropy preprocessed Chan… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 46 REFERENCES

E

X. Bresson
  • S, P. Vanderheynst, J.P. Thiran, S. Osher, Fast global minimization of the active contour/snake model, J. Math. Imaging and Vision 28
  • 2007
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Supervised Descent Method and Its Applications to Face Alignment

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 1 EXCERPT

Adaptive Pipeline Parallelism for Image Feature Extraction Algorithms

  • 2012 41st International Conference on Parallel Processing
  • 2012
VIEW 1 EXCERPT

Face detection

X. Zhu, D. Ramanan
  • pose estimation, and landmark localization in the wild, in: Proceedings of the CVPR
  • 2012
VIEW 1 EXCERPT