ML Anthology

Fast LBP Face Detection on Low-Power SIMD Architectures

Olexa Bilaniuk, Ehsan Fazl Ersi, Robert Laganière, Christina Xu, Daniel Laroche, Craig Moulder
CVPRW 2014 pp. 630-636
doi:10.1109/CVPRW.2014.96 /cvprw/2014/bilaniuk2014cvprw-fast-a/

Abstract

This paper presents an embedded implementation of a face detection method based on boosted LBP features for Single Instruction Multiple Data (SIMD) architectures. The implementation exploits parallelism and data reuse in the detection algorithm and is integrated into CogniVue's Gen-1 APEX platform, which uses a SIMD design and is extremely energy efficient. The proposed embedded face detection system runs at 5 VGA frames per second, while providing similar accuracy to the PC version of the LBP face detection algorithm included in the OpenCV library.

CVPRW Semantic Scholar

Cite

Text

Bilaniuk et al. "Fast LBP Face Detection on Low-Power SIMD Architectures." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014. doi:10.1109/CVPRW.2014.96

Markdown

[Bilaniuk et al. "Fast LBP Face Detection on Low-Power SIMD Architectures." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014.](https://mlanthology.org/cvprw/2014/bilaniuk2014cvprw-fast-a/) doi:10.1109/CVPRW.2014.96

BibTeX

@inproceedings{bilaniuk2014cvprw-fast-a,
  title     = {{Fast LBP Face Detection on Low-Power SIMD Architectures}},
  author    = {Bilaniuk, Olexa and Ersi, Ehsan Fazl and Laganière, Robert and Xu, Christina and Laroche, Daniel and Moulder, Craig},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2014},
  pages     = {630-636},
  doi       = {10.1109/CVPRW.2014.96},
  url       = {https://mlanthology.org/cvprw/2014/bilaniuk2014cvprw-fast-a/}
}