Hough Networks for Head Pose Estimation and Facial Feature Localization

Gernot Riegler, David Ferstl, Matthias Rüther and Horst Bischof

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.66

Abstract

We present Hough Networks (HNs), a novel method that combines the idea of Hough Forests (HFs) with Convolutional Neural Networks (CNNs). Similar to HFs we perform a simultaneous classification and regression on densely extracted image patches. But instead of a Random Forest we utilize a CNN which is able to learn higher-order feature representations and does not rely on any handcrafted features. Applying a CNN on a patch level has the advantage of reasoning about more image details and additionally allows to segment the image into foreground and background. Furthermore, the structure of a CNN supports efficient inference of patches extracted from a regular grid. We evaluate HNs on two computer vision tasks: head pose estimation and facial feature localization. Our method achieves at least state-of-the-art performance without sacrificing versatility which allows extension to many other applications.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 90K)

Paper (PDF, 12 pages, 237K)

Bibtex File

Citation

Gernot Riegler, David Ferstl, Matthias Rüther, and Horst Bischof. Hough Networks for Head Pose Estimation and Facial Feature Localization. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.66
	title = {Hough Networks for Head Pose Estimation and Facial Feature Localization},
	author = {Riegler, Gernot and Ferstl, David and Rüther, Matthias and Bischof, Horst},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.66 }
}