ML Anthology

Exploiting Perception for Face Analysis: Image Abstraction for Head Pose Estimation

Anant Vidur Puri, Brejesh Lall
ECCV 2012 pp. 319-329
doi:10.1007/978-3-642-33868-7_32 /eccv/2012/puri2012eccv-exploiting/

Abstract

We present an algorithm to estimate the pose of a human head from a single, low resolution image in real time. It builds on the fundamentals of human perception i.e. abstracting the relevant details from visual cues. Most images contain far too many cues than what are required for estimating human head pose. Thus, we use non-photorealistic rendering to eliminate irrelevant details like expressions from the picture and accentuate facial features critical to estimating head pose. The maximum likelihood pose range is then estimated by training a classifier on scaled down abstracted images. The results are extremely encouraging especially when compared with other recent methods. Moreover the algorithm is robust to illumination, expression, identity and resolution.

PDF ECCV Semantic Scholar

Cite

Text

Puri and Lall. "Exploiting Perception for Face Analysis: Image Abstraction for Head Pose Estimation." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33868-7_32

Markdown

[Puri and Lall. "Exploiting Perception for Face Analysis: Image Abstraction for Head Pose Estimation." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/puri2012eccv-exploiting/) doi:10.1007/978-3-642-33868-7_32

BibTeX

@inproceedings{puri2012eccv-exploiting,
  title     = {{Exploiting Perception for Face Analysis: Image Abstraction for Head Pose Estimation}},
  author    = {Puri, Anant Vidur and Lall, Brejesh},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {319-329},
  doi       = {10.1007/978-3-642-33868-7_32},
  url       = {https://mlanthology.org/eccv/2012/puri2012eccv-exploiting/}
}